# AI in International Higher Education – Professional Field Guide
## **Introduction – From Concept to Everyday Use**
Artificial Intelligence is no longer a distant concept in international higher education—it’s part of our daily toolkit.\
From handling thousands of visa queries to creating culturally sensitive program materials, AI enables International Education Professionals to **work smarter, serve students better, and strengthen institutional global reach**.
This module moves from theory to practice, showing you **how AI tools can function as chatbots, assistants, and autonomous agents**—and how to match these roles to your specific IHE objectives.
***
### **1. Three Core AI Roles in International Higher Education**
When thinking about AI, it’s more strategic to classify tools by **function**, not brand. This helps you adapt as technologies change.
* **Chatbots** – Ready-to-use conversational tools for answering questions and delivering quick guidance.
* **Assistants** – AI customised with your institutional data via Retrieval-Augmented Generation (RAG), giving context-rich, accurate, and policy-aligned responses.
* **Agents** – Highly automated systems that integrate with institutional platforms (LMS, CRM, SIS) to perform proactive, continuous, multi-step tasks.
***
### **2. Capability Matrix – How Today’s Tools Serve Each Role**
| Tool | **Chatbot** (Out of the Box) | **Assistant** (Custom-configured + RAG) | **Agent** (Advanced Automation) |
| ----------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------- |
| **ChatGPT (OpenAI)** | Multilingual Q\&A, drafting student comms, summarising articles. | Custom GPTs trained on institutional docs for policy-aligned answers, curriculum development support, and program info. | Integrated with APIs to flag at-risk students, generate follow-up comms, and update program data in real time. |
| **Microsoft 365 Agents** ([link](https://adoption.microsoft.com/en-us/ai-agents/agents-in-microsoft-365/?utm_source=chatgpt.com)) | Answers inside Word, Excel, Outlook; meeting summaries in Teams. | Uses SharePoint & Teams files to produce targeted briefs, agreements, or compliance reports. | Automates scheduling, database updates, and departmental routing for inquiries. |
| **Claude for Education (Anthropic)** ([link](https://www.anthropic.com/news/advancing-claude-for-education?utm_source=chatgpt.com)) | Q\&A with strong ethical reasoning. | Integrates with LMS to produce course summaries, study guides, or policy briefs. | Monitors forums, flags unanswered questions, and prompts faculty follow-up. |
| **Perplexity** | Cited live web answers for research queries. | Uses institutional repositories to produce literature reviews and market scans. | Generates automated recruitment intelligence reports from market + CRM data. |
| **Gemini (Google)** | Text, translation, and image Q\&A. | Pulls from stored multimedia to produce virtual campus tour scripts and event content. | Creates multimedia modules and orientation videos with real-time schedule updates. |
| **Poe** | Multi-model access for quick answers. | Hosts fully customised bots with RAG for admissions, advising, or partner relations. | Orchestrates multi-step workflows from query intake to CRM updates. |
| **Adobe Firefly** | Quick text-to-image for visuals. | Generates branded visuals from templates for course materials and events. | Auto-produces full visual packs tied to academic calendars. |
| **MidJourney** | Artistic imagery from prompts. | Fine-tuned prompts for culturally inclusive campus visuals. | Batch-generates region-specific campaign visuals tied to recruitment cycles. |
| **Suno** | Simple music and soundscapes. | Creates branded audio from style briefs for events. | Auto-curates event playlists based on themes and attendee data. |
| **Runway ML** | Text-to-video generation. | Uses institutional footage for customised educational videos. | Auto-generates termly highlight reels from stored clips and program data. |
***
### **3. Applying AI Across the IHE Lifecycle**
#### **Recruitment & Admissions**
* Chatbot: Answer application and visa FAQs instantly.
* Assistant: Custom-trained bot that checks applicant status against SIS data.
* Agent: Automatically reviews application data for completeness, triggers reminders, and updates CRM records.
#### **Student Support**
* Chatbot: Directs students to key support services and FAQs.
* Assistant: Provides culturally nuanced academic advice from policy documents.
* Agent: Monitors engagement, flags at-risk students, and triggers targeted outreach.
#### **Academic Partnerships**
* Chatbot: Shares key facts about your institution with prospective partners.
* Assistant: Summarises MOU terms and partnership impact reports.
* Agent: Tracks collaboration KPIs, sends updates, and automates reporting cycles.
#### **Mobility & COIL**
* Chatbot: Lists available exchange and virtual mobility opportunities.
* Assistant: Matches students to programs based on profile and preferences.
* Agent: Manages end-to-end student placement workflow with partner institutions.
***
### **4. Prompting for International Education**
Effective use of AI depends on **how you ask**.
* **Chain of Thought**: Ask for step-by-step reasoning (e.g., “List all steps for a summer school partnership in Japan, including risk and visa considerations”).
* **Few-Shot Learning**: Give examples first to shape tone and structure (e.g., past program descriptions).
* **RAG**: Link AI to your internal resources so answers match institutional policies.
***
### **5. Building Your Own Institutional AI Agents**
Platforms like **Poe** or custom GPT builders make this accessible:
1. Define your AI’s **role** (e.g., “International Student Visa Advisor”).
2. Set **tone** (professional, culturally sensitive, concise).
3. Upload **knowledge base** (FAQs, handbooks, policies).
4. Apply **ethical guardrails** (no legal advice, privacy-first).
5. Test, gather feedback, and iterate.
***
### **6. Implementation Framework for IE Teams**
1. **Map** – Identify where AI can save time or add value.
2. **Select** – Match tool and role to task.
3. **Pilot** – Start in one functional area.
4. **Measure** – Track KPIs (student satisfaction, processing time).
5. **Refine** – Update prompts, workflows, and knowledge regularly.
***
### **7. Risks & Responsibilities**
* **Bias** – Review outputs for equity and inclusivity.
* **Privacy** – Comply with GDPR and local data laws.
* **Over-Automation** – Keep human oversight in critical decisions.
* **Representation** – Ensure content reflects your student body authentically.
***
### **Closing Perspective**
AI is not replacing the human connection at the core of International Education—it’s amplifying it.\
When used thoughtfully, AI supports faster responses, richer engagement, and a more personalised experience for students and partners around the globe.
# AI in International Higher Education – The Field Guide for Marketers and Strategists
Artificial Intelligence isn’t just the latest tech buzzword, it’s rapidly becoming the connective tissue of the international higher education (IHE) ecosystem.
### **Introduction: A New Era of Global Education**
\
From recruitment offices in Lagos to research labs in Berlin, AI is quietly transforming how institutions attract, engage, and support learners worldwide. For international education marketers and strategists, this is more than a technology shift. It’s a chance to reimagine every stage of the student journey — at scale, across borders, and in multiple languages — while aligning with the values of inclusion, equity, and sustainability.
***
### **1. Why AI Matters for International Higher Education**
In the past, scaling global engagement meant adding more people, more travel, and more budget. AI changes that equation.\
Today’s AI systems can:
* Personalise outreach for millions of prospective students simultaneously.
* Translate complex academic content into dozens of languages in seconds.
* Predict which applicants are most likely to accept an offer — and which might need extra support.
* Create culturally adapted marketing materials without a 6-month creative cycle.
This isn’t replacing human expertise — it’s amplifying it. And in a sector where relationships, trust, and nuance matter, *how* you use AI is as important as the technology itself.
***
### **2. Mapping AI Opportunities Across the IHE Landscape**
We can break the opportunities into **15 core areas of IHE**, each with specific marketing and engagement potential.
#### **International Student Recruitment**
AI analytics can identify untapped markets, segment audiences by cultural preferences, and automate personalised campaigns. Imagine knowing which cities in Vietnam are most likely to produce applicants for a new STEM program — and tailoring ads in the right dialect with the right imagery.
#### **Education Abroad**
Virtual tours powered by AI-driven VR can bring your campus to a student’s phone in Nairobi. Intelligent matching tools can recommend programs based on academic goals *and* personality fit, making your offering stand out in crowded markets.
#### **Admissions**
From multilingual chatbots answering application questions 24/7 to document verification tools that detect fraud, AI removes friction from the decision to apply — a critical point in conversion.
#### **Global Engagement & Partnerships**
AI can scan global research databases, social networks, and government reports to identify new partner institutions that align with your strategic priorities. For marketing teams, that means fresher collaboration stories and joint campaign opportunities.
#### **Student Support**
Generative AI assistants can answer housing, visa, and academic queries instantly — in the student’s preferred language — while alerting staff to students at risk of disengaging.
#### **International Marketing**
Natural language generation can produce ad copy, blog posts, and video scripts optimised for specific audiences. Social listening tools powered by AI track brand sentiment in different regions so campaigns can pivot in real time.
#### **Internationalisation at Home**
AI translation and subtitling make cross-cultural events accessible to all students, allowing marketers to showcase inclusive campus life to prospective students globally.
#### **Transnational Education**
Curriculum localisation tools adapt course content for regional contexts without losing academic integrity, giving marketing teams confidence when promoting offshore programs.
#### **Research Partnerships**
AI research assistants can identify funding opportunities and match academics to collaborators worldwide, creating powerful PR stories about impact-driven research.
#### **Virtual Mobility & COIL**
Adaptive platforms match students to virtual exchange projects that fit their skills and interests, creating new alumni stories for marketing.
#### **Global Summer Schools**
Automated application management frees marketing teams to focus on storytelling — highlighting unique program experiences across social media channels.
#### **Pathways**
Predictive analytics identify which pathway students are most likely to progress successfully, informing retention-focused messaging.
#### **Global HEDTech**
Marketers can showcase AI-enabled learning platforms as part of their institution’s innovation narrative — an increasingly attractive differentiator.
#### **Capacity Building & Training**
Highlight AI-powered professional development initiatives to position the institution as a forward-thinking partner for faculty and staff globally.
#### **Policy & Governance**
AI tools can simulate policy changes’ impact on mobility and recruitment, helping communications teams prepare proactive messaging for stakeholders.
***
### **3. The Risks and Responsibilities**
AI can be a marketing superpower — but it comes with pitfalls.
* **Bias**: Algorithms trained on narrow datasets can reinforce inequities in recruitment and admissions.
* **Privacy**: Mishandling applicant data can undermine trust across markets.
* **Over-automation**: Over-reliance on bots risks depersonalising your brand voice.
Successful teams position AI as *augmentation*, not replacement — ensuring every automated touchpoint feels authentic and human-led.
***
### **4. Future Horizons for IHE Marketing**
* **Spatial Intelligence**: AI that “sees” and “understands” visual, auditory, and text-based environments will create immersive student interactions.
* **Regulation**: The EU AI Act will categorise education-related AI as *High Risk*, meaning transparency and compliance will be marketing talking points.
* **AGI/ASI**: While years away, the leap to Artificial General Intelligence will spark a new wave of hyper-personalised, real-time global engagement.
***
### **5. The Marketer’s AI Action Plan**
1. **Audit** your current student journey and identify friction points AI can address.
2. **Pilot** AI in one or two high-impact areas — e.g., multilingual prospect engagement or content personalisation.
3. **Measure** performance rigorously to demonstrate ROI and guide scaling.
4. **Train** staff in AI literacy, ethics, and cross-cultural sensitivity.
5. **Align** every AI initiative with your institution’s internationalisation strategy and DEI commitments.
***
### **6. Closing Thought**
International higher education has always been about connecting people across borders. AI is simply the newest — and potentially most powerful — bridge we’ve ever had. For marketers and strategists, the goal isn’t just to adopt AI — it’s to ensure that every algorithm, every chatbot, every generated word carries your institution’s *human* story across the world.
# Chatbots, AI Assistants and Agents in International Education
A comprehensive overview of applied Generative AI in International Higher Education.
### A. Chatbots – The Information Responders
What they are:\
Chatbots are the front-line responders — available 24/7 to answer common questions, guide users through simple processes, and point them to the right resources. They draw from pre-loaded information such as admissions FAQs, visa guidance, or accommodation details, and hand more complex cases over to human staff.
How this could look in practice:
* At a large research-intensive university in the UK, a chatbot handles routine visa, CAS, and accommodation questions for incoming international students, and flags unusual queries for an adviser.
* At an urban US public university, a multilingual chatbot answers “Can I use TOEFL Home Edition?” or “When is the I-20 issued?” and connects students to live staff during business hours.
* At a comprehensive Malaysian university, a chatbot on the English-language site provides entry requirements by country and links directly to relevant scholarship pages.
***
#### B. AI Assistants – The Collaborative Partners
What they are:\
AI Assistants are *customised chatbots with superpowers*. They’re configured with tailored instructions and access to curated institutional knowledge bases — think programme catalogues, policy manuals, marketing style guides, or recruitment playbooks. Instead of just answering questions, they *work alongside staff* to draft, analyse, translate, and summarise — always with human review for accuracy and tone.
How this could look in practice:
* At a Canadian provincial university, the marketing team drafts programme pages for India and Vietnam using an AI Assistant, then edits for tone and compliance.
* At a German applied sciences institution, the careers team drafts bilingual employer outreach emails and translates internship ads for incoming exchange students.
* At a private university in Japan, the planning office uses an AI Assistant to summarise enrolment trends and create a briefing on diversifying source markets beyond East Asia.
***
#### C. AI Forms – The One-Time Specialists
What they are:\
AI Forms are short, targeted interactions — a user fills in a few fields, and the AI instantly produces personalised content or recommendations. They can work as stand-alone tools or be triggered as one-off “callouts” within a chatbot or AI Assistant conversation (e.g., a chatbot asking a few structured questions before producing a tailored programme list).
They’re ideal for quick, one-off tasks where you don’t need an ongoing conversation but still want tailored outputs.
How this could look in practice:
* At a metropolitan university in the UAE, a “Find your programme” form asks about budget, language preference, and internship needs, then lists three matching degrees with entry criteria.
* At a regional public university in Spain, a form maps a student’s IELTS score, prior credits, and intended major to the right pathway or foundation option and start term.
* At a teaching-focused South African college, a careers micro-form pairs final-year international students with alumni mentors in their home country and drafts the first outreach email.
***
#### D. Agents – The Autonomous Problem-Solvers
What they are:\
Agents are the “set it and let it run” AI tools. They work in the background, watching for patterns, deadlines, or risk signals, and taking action automatically — from sending alerts to opening internal tickets. They can draw on multiple data sources, adapt to changes, and keep processes moving without constant staff involvement.
How this could look in practice:
* At a national polytechnic in Southeast Asia, an agent monitors LMS logins, missed assessments, and attendance, alerting success coaches when international students are at risk.
* In a multi-campus public system in Australia, an agent keeps track of partner MoU expiry dates, credit-mapping changes, and TNE compliance deadlines, opening tickets ahead of time.
* At a flagship Nigerian university, a market-scan agent monitors visa policy changes in key destinations and posts weekly summaries to the recruitment team.
***
### The Overlap & Flexibility (Higher-Ed View)
* Same tool, different role: one system could be a chatbot on the admissions site, an AI Assistant for drafting offer emails, an AI Form producing personalised programme lists, and an agent monitoring student risk — all in the same ecosystem.
* Brand ≠ function: what matters is configuration, data quality, and governance — not the vendor’s marketing label.
***
### Implementation Tips for IHE
* Start with one clear need: e.g., reduce visa enquiry volume, or automate credit-transfer FAQs for your top sender countries.
* Connect to a trusted knowledge base: admissions handbooks, partner matrices, policy docs — and keep human review in the loop.
* Localise with intention: build country-specific content (requirements, deadlines, scholarships) and make sure your AI references that, not generic copy.
* Put governance first: publish what each tool does, log interventions and hand-offs, and review outputs for bias and accessibility (e.g., language level, screen-reader checks).
***
### Benefits at a Glance
| Role | Speed | Personalisation | Autonomy | Best For | Example Scenario |
| ------------- | ----- | --------------- | -------- | ---------------------------- | --------------------------------------------- |
| Chatbots | High | Low–Med | Low | FAQs, general info | UK university chatbot for visa/CAS questions |
| AI Assistants | Med | High | Low–Med | Drafting, analysis | Canada university: page drafts + localisation |
| AI Forms | High | High | Low | Quick, tailored outputs | Spain: pathway mapping via IELTS & credits |
| Agents | Med | High | High | Monitoring, proactive action | AUS system: partner compliance tracking |
***
### Future Outlook
Expect more blended roles — for example, a chatbot that escalates to an AI Assistant for drafting a personalised email, calls an AI Form to gather structured details, while an agent logs the case and tracks follow-up. The priority for HEIs should be configuring the tools well, feeding them high-quality, up-to-date data, and building staff confidence in using them — rather than chasing the latest tool name.
# GPT‑5 Cookbook for International Education
A practical guide for international education teams. A series of copy‑paste prompts, concrete examples, and clear guardrails.
***
#### What’s new with ChatGPT (GPT-5 and GPT-5.2)
**How it differs from earlier ChatGPT models (quick view):**
* **Unified experience (GPT-5 family):** GPT-5 blends fast chat and deep reasoning. For tough tasks, pick a GPT-5 Thinking option (on paid tiers) or say `think this through`.
* **Better instruction-following:** Sticks to tone, steps, and formats (tables and checklists) with less cleanup.
* **Longer context handling:** More reliable with multi-file handbooks, scholarship sheets, and FAQs.
* **Clearer uncertainty:** More likely to say "needs confirmation" instead of guessing.
* **Improved localisation:** Stronger with country-specific rules, dates, and plain-English rewrites.
**What GPT-5.2 adds on top of GPT-5 / 5.1 (for you and your tech colleagues):**
* **More disciplined answers:** GPT-5.2 is less verbose by default and keeps closer to the requested format (for example, 3–6 bullets, short emails, tables) which is useful for templates, checklists, and student-facing copy.
* **Stronger instruction adherence:** Better at sticking to your exact prompt, including sector-specific tone and sector rules, and at avoiding drift into off-topic content.
* **Better structured reasoning:** Improved performance on complex, multi-step tasks such as comparing handbooks, mapping TNE clauses, or building seminar plans.
* **Smarter tool use:** Works more reliably with web search, file uploads, and internal tools; better at grounding answers in documents instead of guessing.
* **Configurable depth for developers:** In the API, GPT-5.2 supports a `reasoning_effort` setting (for example `none`, `low`, `medium`, `high`) so technical teams can choose between faster responses and deeper reasoning for agents and workflows.
Previously selectable modes you may have seen: GPT-3.5, GPT-4, GPT-4o, GPT-4.1/4.1 mini, o1 (preview/mini), o3, o4-mini. These models still exist and some developers are still building tools with them until OpenAI deprecates them. It is possible that OpenAI might bring some back depending on user feedback.
#### Before you start (ChatGPT setup)
* Open the ChatGPT app (web or mobile) and choose GPT-5 (or GPT-5.2, if available) in the model picker (if available in your plan).
* For tougher or high-stakes tasks, select a GPT-5 Thinking option (if available), or simply add: `think this through` or `explain your plan first`.
* For faster replies, add `quick answer` or ask for `a short paragraph` or `3–5 bullets`.
***
#### Tool & mode quick picks (from the beginner guide, adapted for IHE)
Use this as a “which feature when” map with ready prompts.
| Tool / Mode | Plan\* | What it’s good for in IHE | Paste-ready starter prompt |
| ----------------------------- | ----------------------------------------------- | ----------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔎 **Search (Web browsing)** | All plans | Live facts (deadlines, fees pages), regulator pages, partner news | `Search the web and summarise the latest [Host Regulator] updates that affect [Program]. Link sources; if unclear, write ‘needs confirmation.’` |
| 🔬 **Deep Research** | Plus / Pro / Team / Enterprise / Edu | Structured literature reviews, strategy scans | `Deep research: Do a literature review on [topic]; peer-reviewed 2015–2025; evidence table + 1-page synthesis; include DOIs.` |
| 🖼️ **Vision (image input)** | All plans | Check posters/booth layouts; read screenshots of policies | `Review this fair poster for clarity and accessibility; suggest 3 improvements; draft alt-text.` |
| 📂 **File uploads** | All plans (higher limits on paid) | Summarise handbooks/FAQs; compare versions | `Using these files—[Admissions Handbook 2025.pdf], [Scholarships 2025.xlsx]—answer: [question]. Cite file + section.` |
| 📊 **Data Analysis** | Plus / Pro / Team / Enterprise / Edu | Clean/aggregate CSV/Excel; simple charts/tables | `From this CSV of applications, produce country-by-country offers, a bar chart, and 3 insights; export a clean CSV.` |
| 📝 **Canvas (doc workspace)** | Plus / Pro / Team / Enterprise / Edu | Drafting one-pagers, emails, briefs collaboratively | `Create a 1-page pre-departure brief for [City] with sections: Etiquette, Transport, Scams, Packing, Scripts, Support.` |
| 📁 **Projects** | Plus / Pro / Team / Enterprise / Edu | Keep research notes & sources together over time | `Start a project ‘International Students & Curriculum Enrichment’; store sources and running synthesis here.` |
| ⚙️ **Custom Instructions** | All plans | Set your team voice and default guardrails | `When I ask about admissions, always cite file + section and prefer newest dated doc.` |
| 🧠 **Memory (opt-in)** | Availability varies by region/plan | Remember non-sensitive preferences (tone, time zone) | `Remember my time zone is [X] and my tone is warm, plain English.` |
| ⏰ **Scheduled tasks** | Pro / Team / Enterprise (availability evolving) | Reminders (e.g., check scholarship page monthly) | `Every month, check [URL] for scholarship updates and draft a 4-bullet summary.` |
\*Plan notes: Availability and limits change over time and by region. If a feature doesn’t appear in your account, check the ChatGPT Help Center or your Admin.
> **Privacy tip:** Use Memory only for non-sensitive preferences (tone, time zone). Never store student data in Memory—keep that in your CRM.
***
#### How to use this guide (2 minutes)
1. Pick a scenario below (e.g., “Admissions missing documents”).
2. Copy the prompt and replace the \[brackets] with your details.
3. Paste into ChatGPT and review the draft it produces.
4. Tidy and send (or escalate to a colleague if it’s sensitive).
5. Save good outputs to your shared folder so your team can reuse them.
When this guide says “AI,” think “supercharged assistant that drafts first versions quickly.” You stay in control.
***
#### Key ideas
* **AI Assistant:** drafts answers, emails, lists, and checklists; you approve.
* **Your knowledge base:** the PDF/Word/Sheet files you already have (admissions rules, scholarship tables, FAQs). If you attach or paste them, the AI can quote and summarize them.
* **Thinking style:**
* **Quick** (fast, good for routine) vs **Thorough** (slower, better for complex or risky).
* **Answer length:**
* **Brief** (3–6 bullets or a short paragraph) vs **Detailed** (full email, plan, or 1-page summary).
* **Escalate to a human** for visas, mental health/welfare, academic appeals, or funding decisions.
***
#### Prompt switches (paste-in toggles)
**What they are:** One-line instructions you paste into your message to steer ChatGPT without touching any settings. Think of them as simple on/off toggles that control depth (Quick/Thorough), length (Brief/Detailed), tone, sourcing, and safety.
GPT-5.2 follows these switches more reliably than earlier models, especially for length and sticking to the requested format.
**How to use them:**
* Place at the start or end of your prompt (either works).
* They affect the current message only; paste again if you want the behavior to persist.
* You can combine several; if two conflict, the last one wins.
* When referencing files, use exact file names and sections so the assistant can cite correctly.
Add any of these lines to the top or bottom of a prompt:
**Use only attachments**
```
Use ONLY the attached files. If you cite a rule, name the file + section.
```
**If unsure**
```
If not in the files, write "needs confirmation" and list what to check.
```
**Quick vs Thorough**
```
Be quick / Be thorough. Plan briefly before answering.
```
**Brief vs Detailed**
```
Keep it brief (3–6 bullets or a short paragraph) / Give a detailed one-pager.
```
**Plan first**
```
Start with a 1-line plan, then answer.
```
**Safety**
```
If risk or crisis terms appear, draft a calm message, include the correct hotline for [Country] and our campus support contacts, and add a one-line internal hand-off note I can paste into [System] (summary + time). Do not provide clinical advice.
```
**Tone**
```
Warm, clear, student-friendly tone.
```
**Localise**
```
Use [Country] requirements and [Time Zone] deadlines.
```
**Why bullets/paragraphs (not word counts)?**
* Easier for staff and students—no counting needed.
* Consistent across languages and screen readers.
* Reduces cut-offs and padding; focuses on substance.
* Maps naturally to outputs (checklists vs short replies).
***
#### 60-minute Quick Start (for a small pilot)
**Goal:** Get value today—no tech setup required.
1. **Gather (10 min):** Find 3–5 files you trust (e.g., “Admissions Handbook 2025”, “Scholarships 2025”, “Visa FAQ”, “Support Directory”).
2. **Choose 1–2 scenarios (5 min):** e.g., “Fair Q\&A replies” and “Admissions missing docs emails.”
3. **Copy the prompts from the scenarios below (15 min).**
4. **Test with real questions from last week’s inbox (20 min).**
5. **Decide next steps (10 min):** keep, tweak, or expand to another scenario.
**Success looks like:** fewer back-and-forth emails, faster first drafts, fewer mistakes in requirements.
***
#### Scenario 1 — Recruitment fair Q\&A (and follow-ups)
**Use when:** prospects ask about entry requirements, fees, scholarships, deadlines.
**Prompt:**
```
You are my Recruitment Fair Assistant.
Use ONLY: [Admissions Handbook 2025.pdf], [Scholarships 2025.xlsx], [FAQ.docx].
Question: "[paste the student’s question]" from [country].
Reply briefly (3–6 bullets or a short paragraph), warm and clear. Include:
- The exact requirement(s) for this student’s country (cite file + section)
- The next step with a link or attachment name
- 2 brief follow-up questions to keep the conversation going
If the answer isn’t in the attachments, say "needs confirmation" and list what to check.
```
**What you’ll get:** a short, accurate reply plus 2 follow-ups.\
**Quality check:** Does the answer name a source (file + section)? If not, mark `needs confirmation`.
***
#### Scenario 2 — Admissions “missing documents” email (humane tone)
**Use when:** an application is incomplete.
**Prompt:**
```
Write a warm email to [Applicant Name] about missing documents for the [Program] starting in [Month Year].
Include:
- A short friendly opener
- A bullet list of the exact missing documents (paste the list below)
- How to submit them: portal + reply-with-attachment
- The deadline in [applicant’s local timezone]
- Mention scholarships only if listed in [Scholarships 2025.xlsx] (cite sheet/row)
Keep it to a short email (6–8 sentences). End with an encouraging line.
```
**Tip:** Paste the list of missing items directly into the prompt.
***
#### Scenario 3 — Education Abroad pre-departure brief
**Use when:** preparing students for a destination.
**Prompt:**
```
Create a 1-page pre-departure brief for [City, Country] for [Discipline] students.
Include:
- Everyday etiquette and classroom norms (3 points)
- Transport, housing, and common scams (5 bullet tips)
- A packing checklist (10 items)
- 3 “what to say” scripts for tricky moments
- Links or titles of our campus support services
Add a "Wellbeing & escalation" box: signpost official university support; avoid diagnosis.
Write in plain language. Avoid stereotypes; focus on practical tips.
```
***
#### Scenario 4 — Student Support first-line triage
**Use when:** a student writes about wellbeing, housing, fees, or admin.
**Prompt:**
```
Classify this student message into {information | book appointment | emergency}. Then:
- If information: give a clear answer + a next-step link.
- If book appointment: draft a short reply with a booking link.
- If emergency keywords appear (self-harm, violence, immediate danger): write a calm, supportive message, include the correct hotline for [Country] and our campus support contacts, and advise immediate human escalation. Add a one-line hand-off note I can paste into [System] (summary + time)
Message: "[paste student message]"
Tone: empathetic, clear, and brief.
Rule of thumb: Anything safety-related → provide hotline + campus support info; do not give clinical advice; include an internal hand-off note template.
```
***
#### Scenario 5 — Transnational Education (TNE) compliance check
**Use when:** checking a partner program against host-country rules.
**Prompt:**
```
Role: Educational Compliance Expert.
Compare our program summary [paste or attach Program Spec] with [paste or attach Host Regulator Rules].
List in a simple table:
- Gaps by clause (what’s missing or mismatched)
- Severity (high/medium/low)
- Evidence we need
- Suggested fix wording (1–2 sentences each)
Cite both sources by clause. Flag uncertainty for human review.
```
**Table headers:** Clause | Gap | Severity | Evidence | Suggested Fix | Source(s)
***
#### Scenario 6 — Global engagement: shortlist partners + draft MoU outline
**Use when:** exploring new partnerships.
**Prompt:**
```
Create a shortlist of 10 potential partners in [Region] for our priorities: [themes, e.g., AI in healthcare; SDG 3; student mobility]. For each institution, provide:
- 2 research overlaps with our strengths
- 1 mobility idea
- Risks/considerations (1 line)
Then write a one-page MoU outline for the top 3 (scope, governance, data sharing, review cycle). Note any policy misalignments explicitly.
Keep it practical.
```
***
#### Scenario 7 — International employability coaching
**Use when:** turning global experiences into job-ready bullets.
**Prompt:**
```
Turn these student reflections into achievement-style CV bullets for roles in [Target Country/Industry]. Use action verb + task + impact. Tag each bullet with the USEM or CareerEDGE element it evidences. Then draft 3 interview stories in STAR format.
Reflections: [paste]
Add a note: "Please review and approve before sending".
```
***
#### Scenario 8 — International marketing: localized content pack
**Use when:** creating market-specific outreach.
**Prompt:**
```
Produce a content kit for [Market] about [Program]:
- 1 hero email (short and punchy—6–8 sentences, local tone and deadlines)
- 3 social posts in the style of [Platform], with appropriate emoji/hashtag norms
- 5 FAQs with exact scholarship lines and dates (cite sheet/row)
- UTM tags for links
- Alt-text suggestions for images
Segment by audience where helpful.
```
***
#### Scenario 9 — Teaching: culturally responsive, personalised seminar generator
**Use when:** you want a seminar that adapts to different cohorts (personalisation at scale).
**Prompt:**
```
Create a 60–90 minute seminar on [Topic] for [Module/Course], [Level], [Modality], class size [n].
Cohort segments: [e.g., international first-year (EAL); commuters; working professionals; neurodiverse; remote across time zones].
Deliver:
- 3 learning outcomes (plain language)
- 5-block session arc with timings (activate → explore → apply → reflect → wrap)
- Per-block adaptations per segment (one line each; asset-based; no stereotypes)
- 2 micro-assessments with model answers
- Academic integrity note (allowed AI use; declaration steps) aligned to [Policy] (cite if attached; otherwise write “needs confirmation” + checks)
- Accessibility checklist (alt-text, captions, reading order)
Output:
- **Table:** Block | Time | Activity | Purpose | Materials | Adaptations (by segment)
- Then 5 practical facilitation tips and 2 culturally relevant example cases (local + global).
Tone: warm, student-friendly, plain language.
```
***
#### Scenario 10 — Research: Deep Research (paid) and a free-tier alternative
**Use when:** conducting an academic literature review or evidence brief.
**Activate Deep Research (paid plans)**
* In a new chat, open Tools (🔧) and select Deep research. (If you use Projects, you can start Deep research inside a project.)
* Expect a multi-minute run with citations; ChatGPT may ask a short setup question first.
* Availability and monthly limits vary by plan; if you don’t see it, use the Free-tier alternative below.
**Prompt — Deep Research ON (example you can paste)**
```
Deep research: Conduct an academic literature review on “learning experiences of international students in the United States and how they enrich curriculum and pedagogy in higher education.”
Scope & rules:
- Peer-reviewed sources only, 2015–2025; prioritise systematic reviews/meta-analyses.
- Include key frameworks where relevant (e.g., internationalisation at home, intercultural competence, global citizenship).
- Deliverables: (1) Evidence map table (Study | Year | Context | Design | N | Findings | Limits); (2) 1-page synthesis (what’s known/unknown; implications for curriculum design); (3) 5 gaps & future research ideas; (4) Full citation list with DOI/URL.
- Do not speculate; if evidence is thin, write “needs confirmation” and list what to check.
```
**Prompt — Free-tier alternative (no Deep Research)**
```
Use web browsing to run a rapid scoping review on “learning experiences of international students in the United States and how they enrich curriculum and pedagogy in higher education.”
Rules to reduce errors:
- Search broadly but **include only peer-reviewed sources** (2015–2025). Prefer systematic reviews/meta-analyses; avoid blogs/forums.
- **No fabricated citations.** If you can’t verify a claim, write “needs confirmation.”
- Limit to **8–12** best sources; provide full citations with DOI/URL.
- Show a short inclusion/exclusion note and any disagreements between studies.
- Output: (1) Evidence table (Study | Year | Context | Design | N | Findings | Limits); (2) 6–8 bullet synthesis; (3) 3 implications for curriculum design.
```
***
#### Do / Don’t (cheat sheet)
**What this is:** A quick safety-and-quality checklist for you and a set of ready-to-paste lines you can drop into your prompt so ChatGPT follows the rules.
**How to use it:**
* Treat each Do/Don’t as a toggle you can paste verbatim (see “Paste-able switches” below).
* Put them at the start or end of your message. If you add several and they clash, the last one wins.
* Use them alongside the Prompt switches section for length/tone.
* Note: ChatGPT cannot escalate or log in your systems; it can only draft the message and a hand-off note for you to paste.
**Paste-able switches**
**Do**
**Keep it short and clear.**
```
Keep it brief (3–6 bullets or a short paragraph) in plain language.
```
**Name your sources.**
```
If you cite a rule, name the file + section.
```
**Save reusable outputs.**
```
Format the answer so I can paste it into our template (title + bullets + source).
```
**Don’t**
**Don’t guess on visas or mental health.**
```
If the question is about visas or welfare/mental health, write "for follow-up by [Team/Office]" and do not give advice; include our contact and hours.
```
**Don’t include sensitive data.**
```
Use only what’s necessary; remove IDs and bank details.
```
**Don’t send without a human check.**
```
Add a one-line Reviewer checklist at the end: key facts, links, and anything needing confirmation.
```
**Mini examples**
* **Admissions reply (short + sourced):**
```
Keep it brief (a short paragraph). Use only the attachments. If you cite a rule, name the file + section. If not in the files, write "needs confirmation" and list checks.
```
* **Student support (safety first):**
```
If distress or danger terms appear, write a calm message, include the correct hotline for [Country] and our campus support contacts, and advise immediate human escalation. Add a one-line hand-off note I can paste into [System] (summary + time).
```
***
#### Governance, privacy, and fairness (simple checklist)
* **Data:** Share only what’s necessary. Remove IDs and bank details. Follow your DPIA/records policy.
* **Bias:** Test content with diverse names and backgrounds. Avoid stereotypes.
* **Accessibility:** Use plain language, headings, and alt-text.
* **Escalation:** Define clear hand-offs for visas, welfare/mental health, appeals, and funding.
* **Audit:** Keep a small log of high-stakes AI outputs (date, purpose, who checked).
**Footer block (paste under each scenario):**
```
Safety & Governance: Use only attached docs; minimise personal data. If uncertain, write "needs confirmation" and list checks. Avoid stereotypes; add alt-text for images. Matters involving visas, welfare/mental health, appeals, or funding must be handled by human staff; include contact details in drafts.
```
***
#### Troubleshooting & quality control
* **If the AI sounds unsure:** It should say `needs confirmation` and list what to verify.
* **Too long?** Say `make it a short paragraph` or `give me 5 bullets`.
* **Misses the point?** Paste the exact sentence from your policy and say `align to this`.
* **Sources conflict?** Choose the newest dated document or escalate.
**Ask the model:** `Score and improve your last answer using this rubric.`
***
#### Quick scoring rubric (18 points)
* **Instruction following (0–3)**
* **Factual accuracy (0–3)**
* **Cultural sensitivity (0–3)**
* **Safety (0–3)**
* **Actionability (0–3)**
* **Source use & citations (0–3)** — names file + section; uses “needs confirmation” correctly.
***
#### Roll-out plan (30/60/90 days)
**Days 0–30:** Pilot 2 scenarios (e.g., fair Q\&A + missing-docs emails). Create a tiny shared library of your best prompts and outputs.\
**Days 31–60:** Add student support triage + pre-departure briefs. Run a 2-hour staff workshop (live practice + do/don’t + escalation rules).\
**Days 61–90:** Extend to TNE checks + partner scouting + marketing kits. Add simple metrics: response time, satisfaction, and error rate.
***
#### Tiny prompt snippets you can copy today
**Cite or say “needs confirmation”**
```
Use only the attachments. If you quote a rule, name the file + section. If not in the KB, write “needs confirmation” and list what to check.
```
**Role clarity**
```
You are a Recruitment Fair Assistant. Keep answers brief (a short paragraph), warm, factual, and cite the KB.
```
**Wellbeing handoff**
```
If distress or danger keywords appear, include the correct hotline for [Country] and our campus support contacts, encourage contacting our support, and add a one-line internal hand-off note I can paste into [System] (summary + time).
```
***
## Appendix
### Example prompt for a web research agent:
{% code expandable="true" %}
```
// You are a helpful, warm web research agent. Your job is to deeply and thoroughly research the web and provide long, detailed, comprehensive, well written, and well structured answers grounded in reliable sources. Your answers should be engaging, informative, concrete, and approachable. You MUST adhere perfectly to the guidelines below.
############################################
CORE MISSION
############################################
Answer the user’s question fully and helpfully, with enough evidence that a skeptical reader can trust it.
Never invent facts. If you can’t verify something, say so clearly and explain what you did find.
Default to being detailed and useful rather than short, unless the user explicitly asks for brevity.
Go one step further: after answering the direct question, add high-value adjacent material that supports the user’s underlying goal without drifting off-topic. Don’t just state conclusions—add an explanatory layer. When a claim matters, explain the underlying mechanism/causal chain (what causes it, what it affects, what usually gets misunderstood) in plain language.
############################################
PERSONA
############################################
You are the world’s greatest research assistant.
Engage warmly, enthusiastically, and honestly, while avoiding any ungrounded or sycophantic flattery.
Adopt whatever persona the user asks you to take.
Default tone: natural, conversational, and playful rather than formal or robotic, unless the subject matter requires seriousness.
Match the vibe of the request: for casual conversation lean supportive; for work/task-focused requests lean straightforward and helpful.
############################################
FACTUALITY AND ACCURACY (NON-NEGOTIABLE)
############################################
You MUST browse the web and include citations for all non-creative queries, unless:
The user explicitly tells you not to browse, OR
The request is purely creative and you are absolutely sure web research is unnecessary (example: “write a poem about flowers”).
If you are on the fence about whether browsing would help, you MUST browse.
You MUST browse for:
“Latest/current/today” or time-sensitive topics (news, politics, sports, prices, laws, schedules, product specs, rankings/records, office-holders).
Up-to-date or niche topics where details may have changed recently (weather, exchange rates, economic indicators, standards/regulations, software libraries that could be updated, scientific developments, cultural trends, recent media/entertainment developments).
Travel and trip planning (destinations, venues, logistics, hours, closures, booking constraints, safety changes).
Recommendations of any kind (because what exists, what’s good, what’s open, and what’s safe can change).
Generic/high-level topics (example: “what is an AI agent?” or “openai”) to ensure accuracy and current framing.
Navigational queries (finding a resource, site, official page, doc, definition, source-of-truth reference, etc.).
Any query containing a term you’re unsure about, suspect is a typo, or has ambiguous meaning.
For news queries, prioritize more recent events, and explicitly compare:
The publish date of each source, AND
The date the event happened (if different).
############################################
CITATIONS (REQUIRED)
############################################
When you use web info, you MUST include citations.
Place citations after each paragraph (or after a tight block of closely related sentences) that contains non-obvious web-derived claims.
Do not invent citations. If the user asked you not to browse, do not cite web sources.
Use multiple sources for key claims when possible, prioritizing primary sources and high-quality outlets.
############################################
HOW YOU RESEARCH
############################################
You must conduct deep research in order to provide a comprehensive and off-the-charts informative answer. Provide as much color around your answer as possible, and aim to surprise and delight the user with your effort, attention to detail, and nonobvious insights.
Start with multiple targeted searches. Use parallel searches when helpful. Do not ever rely on a single query.
Deeply and thoroughly research until you have sufficient information to give an accurate, comprehensive answer with strong supporting detail.
Begin broad enough to capture the main answer and the most likely interpretations.
Add targeted follow-up searches to fill gaps, resolve disagreements, or confirm the most important claims.
If the topic is time-sensitive, explicitly check for recent updates.
If the query implies comparisons, options, or recommendations, gather enough coverage to make the tradeoffs clear (not just a single source).
Keep iterating until additional searching is unlikely to materially change the answer or add meaningful missing detail.
If evidence is thin, keep searching rather than guessing.
If a source is a PDF and details depend on figures/tables, use PDF viewing/screenshot rather than guessing.
Only stop when all are true:
You answered the user’s actual question and every subpart.
You found concrete examples and high-value adjacent material.
You found sufficient sources for core claims.
############################################
WRITING GUIDELINES
############################################
Be direct: Start answering immediately.
Be comprehensive: Answer every part of the user’s query. Your answer should be very detailed and long unless the user request is extremely simplistic. If your response is long, include a short summary at the top.
Use simple language: full sentences, short words, concrete verbs, active voice, one main idea per sentence.
Avoid jargon or esoteric language unless the conversation unambiguously indicates the user is an expert.
Use readable formatting:
Use Markdown unless the user specifies otherwise.
Use plain-text section labels and bullets for scannability.
Use tables when the reader’s job is to compare or choose among options (when multiple items share attributes and a grid makes differences pop faster than prose).
Do NOT add potential follow-up questions or clarifying questions at the beginning or end of the response unless the user has explicitly asked for them.
############################################
REQUIRED “VALUE-ADD” BEHAVIOR (DETAIL/RICHNESS)
############################################
Concrete examples: You MUST provide concrete examples whenever helpful (named entities, mechanisms, case examples, specific numbers/dates, “how it works” detail). For queries that ask you to explain a topic, you can also occasionally include an analogy if it helps.
Do not be overly brief by default: even for straightforward questions, your response should include relevant, well-sourced material that makes the answer more useful (context, background, implications, notable details, comparisons, practical takeaways).
In general, provide additional well-researched material whenever it clearly helps the user’s goal.
Before you finalize, do a quick completeness pass:
Did I answer every subpart
Did each major section include explanation + at least one concrete detail/example when possible
Did I include tradeoffs/decision criteria where relevant
############################################
HANDLING AMBIGUITY (WITHOUT ASKING QUESTIONS)
############################################
Never ask clarifying or follow-up questions unless the user explicitly asks you to.
If the query is ambiguous, state your best-guess interpretation plainly, then comprehensively cover the most likely intent. If there are multiple most likely intents, then comprehensively cover each one (in this case you will end up needing to provide a full, long answer for each intent interpretation), rather than asking questions.
############################################
IF YOU CANNOT FULLY COMPLY WITH A REQUEST
############################################
Do not lead with a blunt refusal if you can safely provide something helpful immediately.
First deliver what you can (safe partial answers, verified material, or a closely related helpful alternative), then clearly state any limitations (policy limits, missing/behind-paywall data, unverifiable claims).
If something cannot be verified, say so plainly, explain what you did verify, what remains unknown, and the best next step to resolve it (without asking the user a question).
```
{% endcode %}
***
# Claude Code Cookbook
## Claude Code Cookbook
Practical patterns for getting the most out of Claude Code, adapted from Boris Cherny's (@bcherny) field-tested workflows shared in January and March 2026. Compiled by [AI For Global Education](https://aiforglobaleducation.org/) as part of our commitment to responsible, practical AI adoption in education and beyond.
***
### Where You Run Claude Code
Claude Code runs across five surfaces: the terminal (CLI), the web at [claude.ai/code](https://claude.ai/code), inside your IDE via native extensions for VS Code, Cursor, Windsurf, and JetBrains, the Claude Desktop app, and the Claude mobile app for iOS and Android. The patterns in this cookbook apply across all of them. Your `CLAUDE.md`, slash commands, agents, hooks, MCP configs, and permissions are all workspace-level settings stored in your repo's `.claude/` directory, so they follow you regardless of which surface you use.
You can move sessions freely between these surfaces. Run `claude --teleport` or `/teleport` to continue a cloud session on your local machine. Run `/remote-control` to control a locally running session from your phone or browser. If you find yourself doing this often, set "Enable Remote Control for all sessions" in `/config` so every session is accessible remotely by default.
The CLI and the VS Code extension share conversation history. You can start a session in the extension and resume it in the terminal with `claude --resume`, or vice versa. If you are working in an external terminal, run `/ide` inside Claude Code to connect it back to your open VS Code window.
The mobile app is a genuine coding surface, not just a monitoring tool. You can write and land code from your phone without opening a laptop. Download the Claude app for iOS or Android and use the Code tab on the left.
The recipes below are written from a terminal-first perspective (that is where Boris Cherny's tips originate), but Section 13 covers IDE-specific features and Section 14 covers Desktop-specific features that layer on top of everything else.
***
### 1. Run Multiple Claudes in Parallel
Don't limit yourself to a single Claude Code session. Run five instances in parallel across numbered terminal tabs (1 through 5), and enable system notifications so you know when any instance needs your input. In VS Code, you can also open multiple conversation tabs within the extension itself, giving you a visual overview of all your active workstreams.
You can also run 5 to 10 additional sessions on [claude.ai/code](https://claude.ai/code) alongside your local terminal instances. Hand off work between local and web sessions freely, kick off new sessions in Chrome, and even start sessions from the Claude iOS app on your phone to check in throughout the day.
For serious parallel work within a single repository, use git worktrees (see Section 15).
{% hint style="info" %} Parallelism lets you keep multiple workstreams moving without context-switching. While one Claude is running tests, another can be refactoring, and a third can be working on docs. {% endhint %}
***
### 2. Use the Best Model with Thinking Enabled
Use Opus with thinking enabled for everything. Even though it is bigger and slower than Sonnet, you have to steer it less and it is better at tool use, making it almost always faster in practice than using a smaller model.
{% hint style="info" %} A slower, smarter model that gets things right the first time beats a faster model that needs multiple correction cycles. {% endhint %}
***
### 3. Invest in Your CLAUDE.md
Your team should share a single `CLAUDE.md` file for the repo. Check it into git. The whole team should contribute to it multiple times a week. Any time Claude does something incorrectly, add that learning to the `CLAUDE.md` so it knows not to repeat the mistake.
Example `CLAUDE.md` structure:
```markdown
# Development Workflow
**Always use `bun`, not `npm`.**
# 1. Make changes
# 2. Typecheck (fast)
bun run typecheck
# 3. Run tests
bun run test -- -t "test name" # Single suite
bun run test:file -- "glob" # Specific files
# 4. Lint before committing
bun run lint:file -- "file1.ts" # Specific files
bun run lint # All files
# 5. Before creating PR
bun run lint:claude && bun run test
```
The `CLAUDE.md` is a living document that captures your team's accumulated knowledge about how Claude should work within your specific codebase.
***
### 4. Use Code Review to Grow CLAUDE.md
During code review, tag `@claude` on your coworkers' PRs to add new rules to the `CLAUDE.md` as part of the PR itself. Use the Claude Code GitHub action (`/install-github-action`) for this.
For example, if you spot a pattern issue in a PR review:
> nit: use a string literal, not ts enum\
> @claude add to CLAUDE.md to never use enums, always prefer literal unions
This is a form of "Compounding Engineering": every review cycle makes Claude permanently smarter about your codebase.
***
### 5. Start Sessions in Plan Mode
Most sessions should start in Plan mode (toggle with `shift+tab` twice in the terminal, or click the mode indicator in VS Code). If your goal is to write a Pull Request, stay in Plan mode and go back and forth with Claude until you are happy with the plan. From there, switch into auto-accept edits mode and Claude can usually one-shot the implementation.
{% hint style="info" %} A good plan is the highest-leverage input you can provide. It aligns Claude's understanding with your intent before any code is written, dramatically reducing wasted cycles. In VS Code, Plan mode is even richer: Claude's plan opens as an editable markdown document where you can leave inline comments before execution begins. {% endhint %}
***
### 6. Create Slash Commands for Repeated Workflows
Use slash commands for every "inner loop" workflow that you perform many times a day. This saves you from repeated prompting and makes it so Claude can use these workflows too. Commands are checked into git and live in `.claude/commands/`.
For example, a `/commit-push-pr` command that handles the full commit, push, and PR creation flow in one step.
{% hint style="info" %} If you find yourself typing the same kind of prompt more than twice, turn it into a slash command. {% endhint %}
***
### 7. Use Custom Agents
Custom agents are a powerful primitive that often gets overlooked. Define a new agent in `.claude/agents/`, then run it with `claude --agent=`. Each agent gets its own system prompt, colour label, and can be restricted to specific tools.
Examples of useful agents:
* **code-simplifier** -- Simplifies code after Claude is done working on it
* **verify-app** -- Has detailed instructions for testing Claude Code end to end
* **ReadOnly** -- Restricted to the Read tool only, so it cannot edit files or run bash. Useful for safe exploration of unfamiliar codebases
Example agent definition (`.claude/agents/ReadOnly.md`):
```markdown
---
name: ReadOnly
description: Read-only agent restricted to the Read tool only
color: blue
tools: Read
---
You are a read-only agent that cannot edit files or run bash.
```
Think of agents as specialised roles. The main Claude session is your generalist; agents handle specific jobs with tighter constraints or tailored instructions. See [code.claude.com/docs/en/sub-agents](https://code.claude.com/docs/en/sub-agents) for the full reference.
***
### 8. Use Hooks Across the Agent Lifecycle
Hooks let you run deterministic logic at specific points in Claude's lifecycle. The `PostToolUse` hook for formatting code is just one example. The full set of hook points gives you much finer control over how Claude behaves.
PostToolUse to auto-format code after every write or edit:
```json
"PostToolUse": [
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": "bun run format || true"
}
]
}
]
```
The `|| true` ensures the hook does not block Claude if the formatter encounters an issue.
Other hook points to consider:
* **SessionStart** -- Dynamically load context each time you start Claude. Useful for injecting environment-specific data or pulling fresh state from external systems.
* **PreToolUse** -- Log every bash command the model runs. Good for audit trails and debugging.
* **PermissionRequest** -- Route permission prompts to WhatsApp (or another channel) for you to approve or deny remotely. Especially useful when Claude is running autonomously and you are away from your machine.
* **Stop** -- Poke Claude to keep going whenever it stops. This turns Claude into a more persistent worker that only pauses when it genuinely needs input.
See [code.claude.com/docs/en/hooks](https://code.claude.com/docs/en/hooks) for the full reference.
***
### 9. Use /permissions Instead of --dangerously-skip-permissions
Never use `--dangerously-skip-permissions`. Instead, use `/permissions` to pre-allow common bash commands that you know are safe in your environment. This avoids unnecessary permission prompts without sacrificing safety.
Most of these are checked into `.claude/settings.json` and shared with the team. Example allowed commands:
* `Bash(bq query:*)`
* `Bash(bun run build:*)`
* `Bash(bun run lint:file:*)`
* `Bash(bun run test:*)`
* `Bash(bun run typecheck:*)`
* `Bash(cc:*)`
* `Bash(find:*)`
{% hint style="info" %} Be explicit about what is safe rather than turning off all safety checks. {% endhint %}
***
### 10. Connect Claude Code to Your Tools via MCP
Claude Code can use all your tools. It can search and post to Slack (via the MCP server), run BigQuery queries to answer analytics questions (using `bq` CLI), grab error logs from Sentry, and more.
The Slack MCP configuration is checked into your `.mcp.json` and shared with the team:
```json
{
"mcpServers": {
"slack": {
"type": "http",
"url": "https://slack.mcp.anthropic.com/mcp"
}
}
}
```
The more tools Claude can access, the more autonomously it can work. Give it access to your observability stack, your project management tools, and your communication channels.
***
### 11. Use /loop and /schedule for Automated Work
Two of the most powerful features in Claude Code are `/loop` and `/schedule`. Use these to have Claude run automatically at a set interval, for up to a week at a time.
Example loops running locally:
* `/loop 5m /babysit` to auto-address code review feedback, auto-rebase, and keep PRs moving
* `/loop` combined with a slash command to periodically check build status or run regression tests
`/schedule` lets you set up one-off or recurring runs at specific times rather than intervals. Both are useful for the kind of background maintenance work that otherwise interrupts your focus.
For very long-running tasks, you can also use these strategies:
* Prompt Claude to verify its work with a background agent when it finishes
* Use a Stop hook to perform verification more deterministically
* Use the ralph-wiggum plugin (a community plugin originally by @GeoffreyHuntley) for managing long-running sessions
Long-running sessions can consume millions of tokens (2.4M+ in some cases) and run for over a day, so having a strategy for verification and recovery is essential. See [code.claude.com/docs/en/schedule](https://code.claude.com/docs/en/schedule) for the full reference.
***
### 12. Give Claude a Feedback Loop
This is probably the most important tip: give Claude a way to verify its work. If Claude has a feedback loop, it will 2 to 3x the quality of the final result.
Claude should test every single change before it lands. This means running typechecks after code changes, running the relevant test suite, linting modified files, and verifying the build still passes.
The combination of a good `CLAUDE.md` (telling Claude how to verify) and pre-allowed permissions (letting Claude verify without interruption) is what makes this feedback loop tight and effective.
#### The Chrome Extension for Frontend Work
For web development, the feedback loop principle extends to the browser. Install the Claude Code Chrome extension (available for Chrome and Edge) to give Claude the ability to see and interact with your running application. Think of it like any other engineer: if you ask someone to build a website but they are not allowed to use a browser, the result probably will not look good. Give them a browser and they will write code and iterate until it does.
The Chrome extension tends to work more reliably than other similar MCP-based browser tools. Use it every time you work on web code. Download the extension at [code.claude.com/docs/en/chrome](https://code.claude.com/docs/en/chrome).
***
### 13. IDE Integration: VS Code as a Worked Example
Everything in the sections above works identically in VS Code (and its forks Cursor and Windsurf). Install the official "Claude Code" extension from the marketplace, and you get a sidebar chat panel backed by the same engine as the CLI. The IDE adds several features worth using deliberately.
#### Richer Plan Mode
In the terminal, Plan mode is a text exchange. In VS Code, Claude's plan opens as a full editable markdown document. You can leave inline comments directly on the plan, and Claude will read and incorporate them before it starts writing code. You are not just approving a plan, you are annotating it.
#### Automatic Context Sharing
The extension automatically shares your currently open file, highlighted selection, and the contents of the Problems panel (lint errors, type errors, diagnostics) with Claude. You can highlight a broken function and type "fix this" without any copy-pasting. In the terminal, you would need to describe the context or use `@` references manually.
#### @-Mentions for Files, Selections, and Terminals
You can reference specific files with `@filename.ts`, include line ranges from your current selection, or pull in terminal output using `@terminal:name` (where "name" is the terminal's tab title). This is especially useful for feeding test failures or build logs into Claude without leaving your editor.
#### Native Inline Diffs
When Claude proposes changes, VS Code shows them in its native diff viewer with accept/reject controls per hunk. This is a significant improvement over the terminal's ANSI-coloured text diffs, especially for large multi-file changes where you want to review carefully.
#### Multiple Conversation Tabs
You can open multiple Claude conversations in separate tabs or windows within VS Code, each scoped to a different task. Combined with the parallel sessions pattern from Section 1, this gives you a visual workspace where each tab is a distinct workstream.
#### Permission Mode Defaults
Set your preferred starting mode in VS Code settings under `claudeCode.initialPermissionMode`. If your team's convention is to always start in Plan mode, you can enforce that as the default so nobody accidentally starts in auto-accept.
#### What the IDE Does Not Replace
A few CLI features do not have full equivalents in the extension yet. Checkpoint management and extended autonomous operation (the kind of multi-hour, multi-million-token sessions described in Section 11) are better suited to the terminal. Background task visibility is also more limited in the extension. For long-running agentic work, the terminal remains the stronger option, and you can always resume that session in VS Code later with `claude --resume`.
***
### 14. The Desktop App and Cowork Dispatch
The Claude Desktop app bundles in the ability for Claude to automatically run your web server and test it in a built-in browser. This makes the feedback loop from Section 12 even tighter for frontend work: Claude writes the code, starts the server, checks the result visually, and iterates, all without you configuring anything. You can set up something similar in the CLI or VS Code using the Chrome extension, but the Desktop app handles it out of the box. See [code.claude.com/docs/en/desktop](https://code.claude.com/docs/en/desktop) for details.
#### Cowork Dispatch
Dispatch is a secure remote control for the Claude Desktop app. It lets you catch up on Slack and emails, manage files, and run tasks on your laptop from your phone, even when you are not at your computer. When you are not coding, you are dispatching.
Dispatch can use your MCPs, browser, and computer, with your permission. It is especially useful for the kind of non-coding work (triaging messages, moving files, checking dashboards) that otherwise pulls you back to your desk.
***
### 15. Use Git Worktrees for Serious Parallel Work
Claude Code ships with deep support for git worktrees. Worktrees are essential for doing lots of parallel work in the same repository. Use `claude -w` to start a new session in a worktree, or check the "worktree" checkbox in the Claude Desktop app.
For non-git version control systems, use the `WorktreeCreate` hook to add your own logic for worktree creation.
#### /batch for Massive Changesets
`/batch` takes parallel work to the extreme. It interviews you about what needs to change, then fans out the work to as many worktree agents as it takes (dozens, hundreds, even thousands) to get it done. Use it for large code migrations and other sweeping changes that would take a human team days or weeks.
***
### 16. Fork Your Session
People often ask how to fork an existing session so they can explore a different direction without losing their current context. Two ways:
1. Run `/branch` from within your session. Claude creates a branched conversation and tells you how to resume the original.
2. From the CLI, run `claude --resume --fork-session`.
This is useful when you want to try an alternative approach to a problem without committing to it, or when a session has built up valuable context that you want to preserve while experimenting.
***
### 17. Use /btw for Side Queries
`/btw` lets you ask quick questions while the agent continues working. It opens a lightweight overlay that does not interrupt Claude's current task.
For example, while Claude is in the middle of a large refactor, you can type `/btw how do I spell dachshund?` and get an instant answer without breaking Claude's flow.
***
### 18. Use --add-dir for Multi-Repo Work
When working across multiple repositories, start Claude in one repo and use `--add-dir` (or `/add-dir` during a session) to give Claude access to the other repo. This not only tells Claude about the second repo but also gives it permissions to read and write there.
For a permanent setup, add `"additionalDirectories"` to your team's `settings.json` so the extra paths are always loaded.
***
### 19. Use --bare for Fast Non-Interactive Startup
By default, when you run `claude -p` (or use the TypeScript or Python SDKs), Claude searches for local `CLAUDE.md` files, settings, and MCPs. For non-interactive usage like scripting or CI pipelines, this overhead is unnecessary and can slow startup by up to 10x.
Use the `--bare` flag to skip all of that. With `--bare`, you explicitly specify what to load, keeping startup fast and predictable.
```bash
claude -p "summarize this codebase" \
--output-format=stream-json \
--verbose \
--bare
```
***
### 20. Use /voice for Voice Input
You can do most of your coding by speaking to Claude rather than typing. Run `/voice` in the CLI, then hold the space bar to speak. On the Desktop app, press the voice button. On iOS, enable dictation in your settings.
Voice input is especially useful for plan-mode conversations where you are describing intent and architecture rather than writing precise code. It is faster than typing for exploratory work.
***
### Quick Reference: File and Config Locations
| File | Purpose |
| ----------------------- | ------------------------------------------------------------------ |
| `CLAUDE.md` | Project instructions, team conventions, and learned mistakes |
| `.claude/commands/` | Slash commands for repeated workflows |
| `.claude/agents/` | Agent definitions with custom system prompts and tool restrictions |
| `.claude/settings.json` | Allowed permissions, preferences, and additional directories |
| `.mcp.json` | MCP server configurations (Slack, etc.) |
***
### Quick Reference: Useful Slash Commands
| Command | What it does |
| ----------------- | --------------------------------------------------------- |
| `/branch` | Fork the current session into a new branch |
| `/btw` | Ask a side question without interrupting the current task |
| `/loop` | Run a prompt repeatedly at a set interval |
| `/schedule` | Schedule a prompt to run at a specific time |
| `/batch` | Fan out a changeset across many worktree agents |
| `/voice` | Enable voice input |
| `/teleport` | Continue a cloud session locally |
| `/remote-control` | Control this session from another device |
| `/permissions` | Manage allowed commands |
| `/ide` | Connect to your IDE from an external terminal |
***
### The Philosophy in Summary
The throughline across all of these patterns is the same: invest upfront in Claude's environment and instructions so that it can work more autonomously, verify its own work, and compound its knowledge over time. Plan before you execute. Encode your learnings. Give Claude the tools and permissions it needs. And always, always give it a way to check its own work.
***
*This resource is maintained by* [*AI For Global Education*](https://aiforglobaleducation.org/) *(UK Charity No. 1213764). AIFGE supports responsible AI adoption in education through open resources, tooling, and community engagement. For more on our work, visit* [*aiforglobaleducation.org*](https://aiforglobaleducation.org/)*.*
# N8N News Automation Recipe for International Education
A guide to build a simple automation using Prompt Engineering in N8N.
Keeping up with fast-moving AI-in-education policy and practice is hard enough. Turning that into a consistent, readable digest (with sources, structure, and a clear “so what?”) is even harder. So we built a lightweight n8n workflow that does two things really well:
**(1) generate a tightly-scoped weekly research brief from trusted sources**, and
**(2) transform that brief into a publish-ready blog-style digest saved straight into Google Docs**.
### Automation at a glance
**Schedule Trigger** → **Perplexity research brief** → **Claude (agent) writes digest** → **Google Doc created** → **digest inserted into that doc** AI in Global Ed News Google Docs AI in Global Ed News Google Docs
Under the hood, the agent is also wired with:
* an **Anthropic chat model** (Claude Opus 4.5), AI in Global Ed News Google Docs
* **memory** keyed to the current run, AI in Global Ed News Google Docs
* and an optional **Perplexity search tool** it can call for clarifications.
### Flow 1: The trigger (when the automation runs)
The workflow starts with n8n’s **Schedule Trigger** node.
In other words: this flow is designed to run on a recurring cadence (daily/weekly/whatever you set in n8n), and every run produces a dated digest document downstream.
### Flow 2: Research brief generation (Perplexity)
#### What the node does
Immediately after the trigger, we call **Perplexity** using the `sonar-pro` model to generate a research brief. AI in Global Ed News Google Docs The node is configured with `searchRecency: "week"` to bias results toward the last seven days.
#### The research prompt (why it’s so strict)
The Perplexity prompt is doing most of the quality control. It:
* sets a clear role (senior research analyst for IHE with AI-in-education focus),
* enforces a **hard 7-day window** (“Treat ‘today’ as {{ $today }}” and exclude older items),
* restricts citations to an **allowlist of domains** (IHE news + policy bodies + major lab/provider blogs + IGOs),
* forces a consistent output structure: executive summary, “what’s new/why it matters,” regional nuances, risks & unknowns, recommendations, and an evidence table with links. AI in Global Ed News Google Docs
That combination matters because it prevents the “AI news” step from drifting into:
* stale coverage,
* random sources of unknown quality,
* or unstructured summaries that are hard to reuse later.
#### The full prompt
{% code expandable="true" %}
```
// You are my Researcher for International Higher Education (IHE) with a specialist focus on AI in education, supporting AI For Global Education (a UK Charitable Incorporated Organisation under the Charities Act 2011).
You MUST:
- Silently execute the task below.
- NOT ask me questions, NOT explain your process, and NOT engage in conversation.
- ONLY output the brief in the exact structure requested.
ROLE & GOAL
- Role: senior research analyst for global higher education policy, markets, mobility, and AI in education.
- Goal: produce concise, evidence-backed briefs on AI in education using only eligible sources from the last 7 days.
- Geographic focus (in order of priority): UK, Europe, US, Australia, China, then wider international higher education.
- Sector focus: higher education and international education, including major school/FE items only where they clearly impact HE or cross-sector policy.
- Treat “today” as {{ $today }}. If coverage is thin, say so—do NOT include older items.
TOPIC & IMPACT SCOPE (internalise)
- Core topic: AI in education (policy, practice, governance, markets, tools, regulation, ethics).
- Focus only on stories where AI is central, not incidental.
- For each item, consider impact across these areas (one or more may apply):
1. Learning and Teaching (curriculum, pedagogy, assessment, student learning experience).
2. Research (funding, collaboration, infrastructure, integrity, methodologies, AI tools in research).
3. Administration and Professional Services (student services, admissions, registry, careers, IT, analytics, QA/QE, finance, HR).
4. International Education Management (internationalisation strategy, student recruitment, marketing, TNE/branch campuses, partnerships, visas, mobility).
IHE CONTEXT (internalise)
International higher education (IHE) weaves international, intercultural, and global dimensions into strategy/governance, teaching/curriculum, research, partnerships, and student services. In practice: recruit/support international students; enable physical/virtual mobility; build cross-border research networks; deliver TNE (branch campuses, joint/dual degrees, online). Work depends on QA, data, tech, finance, and wellbeing; shaped by immigration policy, funding, export and visa regimes, and digital/AI regulation. Drivers: talent needs and competition. Pressures: geopolitics, demographics, climate sustainability, commercialisation vs public good, equity/inclusion, academic freedom, and responsible AI governance. AI can amplify both the opportunities and the risks in all these domains.
SOURCE POLICY (allowlist; cite ONLY these)
Use ONLY the domains below for factual claims and citations. If a relevant item is outside this allowlist or outside the 7-day window, say so briefly rather than citing it.
Paywalls:
- Paywalled sources are allowed.
- You do NOT need to label items as paywalled.
Prioritise sources in this order when multiple cover the same story:
1) IHE/education news & policy bodies
2) Official blogs from major AI/tech providers
3) Practitioner/analysis blogs and think tanks
A. International higher education & education news
- timeshighereducation.com
- universityworldnews.com
- thepienews.com
- insidehighered.com
- chronicle.com
- monitor.icef.com
- wenr.wes.org
- topuniversities.com
- qs.com
- researchprofessionalnews.com
- theguardian.com
- bbc.co.uk
- bbc.com
- al-fanarmedia.org
- edsurge.com
- edtechmagazine.com
- hechingerreport.org
- educause.edu
B. AI & major tech provider official blogs / education pages
(Use for launches, feature descriptions, and stated intentions. Treat strong impact claims cautiously unless supported elsewhere.)
- openai.com (including /blog, /education)
- microsoft.com (including blogs.microsoft.com, education.microsoft.com, learn.microsoft.com)
- google.com, blog.google, edu.google.com
- anthropic.com and claude.ai
- meta.com and ai.meta.com
- deepmind.google
- ibm.com (AI / education content)
- aws.amazon.com (including /blogs)
- salesforce.com (education & AI content)
C. International organisations & policy / standards bodies
(Use for AI, education, skills, and digital policy, especially where it shapes HE and IHE.)
- unesco.org
- oecd.org and oecd.ai
- worldbank.org (education & digital sections)
- european-union.europa.eu
- european-commission.europa.eu
- gov.uk (relevant UK AI/education/HE policy – e.g., DfE, DSIT)
- officeforstudents.org.uk
- jisc.ac.uk
- qaa.ac.uk
D. Practitioner / analysis blogs & think tanks (AI in education, HE)
(Use for expert commentary, case studies, and sense-making; clearly distinguish opinion/analysis from reported facts.)
- oneusefulthing.org (Ethan Mollick)
- brookings.edu
- rand.org
- oii.ox.ac.uk (Oxford Internet Institute)
General rules
- Do NOT cite domains outside this list for factual claims.
- Where vendor or practitioner sources make strong claims about impact, treat them as perspectives unless supported by news/policy/IGO sources.
- If none of the allowlisted sources cover an important development within the 7-day window, state: “No coverage found in allowlisted sources within the 7-day window.”
- Exclude sources if you are unsure whether they fall within the 7-day window.
HARD DATE WINDOW (strict)
- Only include items published within the last 7 days relative to {{ $today }}.
- If an article shows an “updated” timestamp, use the original publication date to enforce the window.
- If you’re unsure whether an item falls within the 7-day window, exclude it.
COVERAGE PRIORITIES
- Prioritise:
- AI in education policy/regulation affecting HE and TNE (e.g., AI exams/assessment rules, visa or funding changes linked to AI skills, AI safety laws with HE implications).
- Institutional uses of AI in HE for teaching, research, student support, and administration.
- International student recruitment, mobility, and partnerships where AI tools, data, or policy play a significant role.
- Within the 7-day window:
- Start with UK, then Europe, US, Australia, China.
- Then include major global or regional IHE/AI stories (e.g., UNESCO, OECD, major cross-border initiatives).
- If there are many items, prioritise those with clearest system-level implications over single-course or single-tool “novelties”.
OUTPUT FORMAT (exact)
- Executive Summary (≤150 words)
- 2–4 key themes linking AI in education to IHE across the 4 impact areas.
- Mention regions covered (e.g., “UK, EU, Australia, and global policy bodies feature this week…”).
- What’s new / Why it matters (bullets)
- Bullet each news item or cluster.
- For each bullet, clearly tag:
- **Region(s)** (e.g., UK, EU, US, Australia, China, Global).
- **Impact area(s)** using labels: [L&T], [Research], [Admin/PS], [IntEd Mgmt].
- Briefly explain why this matters for:
- universities and colleges;
- international offices / TNE leaders;
- and (where relevant) AI For Global Education’s mission (ethical, equitable AI in education).
- Regional nuances (if any)
- Short section (paragraph or bullets).
- Compare/contrast how AI in education is evolving across key regions (UK/EU/US/Australia/China/other).
- Note where approaches diverge on:
- regulation and ethics;
- use of AI in assessment and admissions;
- use of AI in international recruitment and marketing;
- funding for AI skills or research.
- Risks & unknowns
- Identify:
- Regulatory and compliance risks (especially for UK-registered charities and HEIs).
- Operational risks (e.g., data protection, bias, academic integrity, over-reliance on vendors).
- Reputational risks (for institutions and for AI in education more broadly).
- Call out gaps in evidence or disagreements between sources.
- If AI policy or regulation is clearly evolving, add a brief “Volatility” note and suggest relevant official trackers (e.g., national regulators, UNESCO/OECD pages) but do not cite them as evidence for specific claims unless on the allowlist.
- Recommendations / next actions (bullets)
- Aim recommendations at:
- senior HE leaders and international offices;
- AI For Global Education as a UK CIO supporting ethical AI in education.
- Examples:
- monitoring / horizon scanning actions;
- policy or governance checks (e.g., AI assessment policy, data sharing with vendors);
- opportunities for partnerships, research, training, or resource development;
- implications for underserved or marginalised learners and how to mitigate inequity.
- Evidence Table (markdown):
Publisher | Title | Date (ISO) | Key finding (≤20 words) | Link
- Include only items you’ve discussed above.
- Maximise diversity of sources within the allowlist.
- Make Key finding specific and linked to at least one of the 4 impact areas.
STYLE & GUARDRAILS
- Neutral, policy-literate tone for HE leaders and international education professionals.
- Assume the audience understands HE and IHE, but not the details of every AI tool or model.
- No hype; avoid vendor marketing language. Focus on policy, impact, and implications.
- No speculation unless clearly labelled as such (e.g., “Speculation:”).
- If sources disagree, summarise both perspectives and note that they diverge.
- Be explicit where evidence mainly concerns one national context and may not generalise.
- Keep all claims grounded in the allowlisted sources and the 7-day window; if something is important but outside the rules, briefly note it as “Out of scope (older than 7 days)” without details.
```
{% endcode %}
### Flow 3: Writing the digest (AI Agent + Claude)
#### Model + agent wiring
The writing step is an **n8n LangChain Agent** powered by an **Anthropic Chat Model** set to `claude-opus-4-5-20251101` (Claude Opus 4.5). AI in Global Ed News Google Docs AI in Global Ed News Google Docs
#### What the agent receives as input
The agent’s input text is the **Perplexity output** (specifically the message content from the prior node): `{{ $json.choices[0].message.content }}`. AI in Global Ed News Google Docs
This is a key design choice: Claude isn’t asked to “browse the web.” It’s asked to write **only from the brief** you just generated.
#### The writing system prompt (structure + guardrails)
The system message for the agent is effectively a “house style + compliance layer.” It instructs the model to:
* write as a professional blog writer for AI For Global Education,
* be interpretative (impact-focused) rather than repeating every item,
* use *only* facts and links contained in the weekly brief,
* avoid hype and keep a policy-literate, practitioner-friendly tone,
* **not use em dashes** (this is explicitly enforced),
* and output a fixed structure: Title, Intro, four required sections (“Learning and Teaching”, “Research”, “Administration and Professional Services”, “International Education Management”), Takeaway, Meta Description (≤155 chars), and SEO keywords. AI in Global Ed News Google Docs
It also forces good citation behaviour *inside the blog post*: “Link 3 to 5 key claims to sources from the brief using markdown links,” and “Use absolute dates (YYYY-MM-DD) for time-sensitive claims.”
#### The full prompt
{% code expandable="true" %}
```
// You are a professional blog content writer for AI For Global Education (a UK Charitable Incorporated Organisation) and its global higher education news and analysis site. You translate the latest developments at the intersection of AI in education and International Higher Education (IHE) into engaging, interpretative blog posts that focus on potential impact, not just reporting news.
You MUST:
- Silently execute the task below.
- NOT ask questions, NOT explain your process, and NOT engage in conversation.
- ONLY output the final blog post content in the structure requested (no extra commentary or headings beyond the blog itself).
- NOT use em dashes (the long dash character). Use simple hyphens (-) or colons (:) instead.
Your task is to write a clear, captivating, and SEO-optimized blog post based only on the Weekly AI-in-Education & IHE Research Brief provided below. Use only the facts and links contained in that brief (last 7 days). The post should be easy to understand, informed, current, and directly relevant to practitioners.
Your role is NOT to list every news item again. Assume the brief already does that. Your job is to:
- Pull out a small number of key themes from the brief.
- Use examples from the brief to illustrate those themes.
- Offer thoughtful commentary on what these developments could mean for:
- Learning and Teaching
- Research
- Administration and Professional Services
- International Education Management
INSTRUCTIONS:
Audience:
Higher education staff working in:
- international offices (recruitment, mobility, partnerships, TNE),
- teaching and learning and curriculum or assessment,
- research management and digital or AI infrastructure,
- professional services (student support, careers, IT, data or analytics),
- policymakers and sector bodies,
plus internationally minded readers who care about responsible AI in education.
Tone & Style:
- Friendly, conversational, and policy-literate.
- Not clickbait, but lively, concrete, and human.
- Avoid jargon; if terms like TNE, large language model (LLM), or post-study work appear, define them simply.
- Avoid AI "hype". Emphasise evidence, context, trade offs, and responsible use.
- Use a short story, metaphor, or real-world example when helpful, but do not invent new factual events.
Format:
- Title (must include primary keywords related to AI in education or higher education).
- 1 paragraph Hook or Intro that:
- Briefly summarizes the main developments in the Weekly Brief in 2 to 4 sentences.
- Mentions the main themes and regions covered, without listing every detail.
- Signals that the post will explore potential impacts for the four focus areas.
- Four required sections, each with the exact subheading names:
- "Learning and Teaching"
- "Research"
- "Administration and Professional Services"
- "International Education Management"
- You may add up to one additional optional section if clearly supported by the brief.
- Final Takeaway / What this means for practitioners.
- SEO Meta Description (max 155 characters).
- Include 3 to 5 SEO keywords naturally in the body.
- Use bullet points or bolding to improve skimmability.
- Do not use em dashes anywhere.
Rules about evidence and interpretation:
- Do not fabricate facts. Use only information and links from the Weekly AI-in-Education & IHE Research Brief (last 7 days).
- You may interpret and extrapolate what developments might mean, but:
- Clearly separate fact from interpretation using language like "could", "may", "is likely to", "one risk is".
- Do not invent specific numbers, policies, or events that are not in the brief.
- Use absolute dates (YYYY-MM-DD) for time-sensitive claims.
- Link 3 to 5 key claims to sources from the brief using markdown links.
- If evidence is thin this week, write a "what this could mean" style piece that focuses on scenarios and questions, without adding new factual claims.
- Keep paragraphs short; avoid buzzwords and unexplained acronyms.
- Do not introduce AI tools, policies, or countries that are not mentioned in the brief.
Impact Focus (interpretative, not descriptive):
Any AI development in the brief can potentially affect several areas. In each section:
- You may pull on the same examples or sources as other sections, but:
- Emphasise a different angle in each section.
- Explain how the same development might land differently for teaching, research, services, or international education management.
You MUST include a subheading and short interpretative section for each of:
1. Learning and Teaching
- Explain how this week’s developments could affect curriculum, pedagogy, assessment, academic integrity, or student support.
- Use 1 to 2 examples from the brief to illustrate possible classroom or online learning impacts.
2. Research
- Explain how developments might shape research funding, methods, collaboration, integrity, or research support services.
- If the brief includes little explicit research content, say so and focus on thoughtful, cautious interpretation.
3. Administration and Professional Services
- Discuss potential implications for admissions, registry, student support, careers, IT, analytics, and governance.
- Focus on workflows, skills, systems, and risk or governance issues highlighted by the brief.
4. International Education Management
- Explore what this week’s AI developments could mean for international recruitment, marketing, visas, mobility, TNE or branch campuses, and partnerships.
- Draw out any regional nuances (UK, Europe, US, Australia, China, others) mentioned in the brief.
Regional Lens (internalise while writing):
- Where relevant, highlight differences or examples from: UK, Europe, US, Australia, China, and wider regions.
- Make it clear when a point is context specific (for example "In the UK" versus "Globally").
Example Topics This Prompt Can Work For:
- "How this week’s AI policy moves could reshape international student recruitment"
- "AI in university classrooms: why this week’s announcements matter for assessment and student support"
- "From back office to front line: what new AI tools could mean for university professional services"
- "Research, regulation, and recruitment: reading this week’s AI news through an international education lens"
STRUCTURE TO FOLLOW IN YOUR OUTPUT (NO LABELS, JUST CONTENT):
[Catchy SEO Blog Title with AI or Higher Education Keyword]
[Optional Subtitle for clarity]
[Intro paragraph]
[A compelling hook that briefly summarizes the main developments from the Weekly Brief, clusters them into 2 to 3 themes, notes key regions, and signals that the post will explore their potential impact across the four areas.]
Learning and Teaching
[1 to 3 short paragraphs. Use 1 to 2 concrete examples or sources from the brief to explore how this week’s AI news could affect teaching practice, assessment, student experience, or academic integrity. Focus on "so what", opportunities, and risks. Include at least one inline source link.]
Research
[1 to 2 short paragraphs. Use information from the brief to discuss potential implications for research funding, collaboration, methods, or integrity. If research specific coverage is limited, say so briefly and focus on cautious interpretation, scenarios, or questions. Include at least one inline source link if possible.]
Administration and Professional Services
[1 to 2 short paragraphs. Interpret how developments described in the brief could reshape professional services such as admissions, registry, student support, careers, IT, analytics, and governance. Consider workflows, staff capacity, data, and risk. Include at least one inline source link if relevant.]
International Education Management
[1 to 3 short paragraphs. Explore how this week’s AI developments might influence international recruitment, marketing, visas, mobility, TNE or branch campuses, and partnerships. Reuse examples from earlier sections if helpful, but from an international education perspective. Highlight any regional nuances mentioned in the brief. Include at least one inline source link.]
[Optional additional section with a relevant subheading, only if clearly supported by the brief and not overlapping the four core areas. This should still be interpretative.]
Takeaway:
[2 to 3 sentence wrap up on what matters this week for practitioners across the four areas, what to watch next, and optionally one reflective question or practical suggestion for teams thinking about AI in their own context.]
Meta Description:
[Short, SEO focused summary of the post. Max 155 characters. Include an AI in education or higher education keyword.]
SEO Keywords:
[3 to 5 relevant AI in education or IHE keywords you used naturally, for example: AI in higher education, international students, AI policy, transnational education, student mobility, academic integrity, digital skills.]
```
{% endcode %}
### Flow 4: Optional accuracy boosters (Memory + Perplexity tool)
Even with a strong brief, we added two optional “stability” helpers:
#### 1) Simple Memory
There’s a **memory buffer** node connected into the agent, using a custom session key based on the Perplexity node’s item id:\
`sessionKey: {{ $('Perplexity - Blog Topic Research Node').item.json.id }}`
Practically, this helps the agent stay coherent within a run (and can help if you later expand to multi-step drafting).
#### 2) Perplexity Search Tool
The agent also has a Perplexity tool available (a callable search tool node). This is there for “when needed” clarification or extra context retrieval without changing your overall architecture.
(You can keep this enabled or disable it if you want stricter containment.)
### Flow 5: Publishing to Google Docs (create + insert)
This workflow doesn’t just output text—it saves it where your editorial process already happens.
#### 1) Create a dated Google Doc
A Google Docs node creates a new doc in a specified folder with a date-based title:
`Global Ed News Digest - {{ $today.toFormat('yyyy-MM-dd') }}` AI in Global Ed News Google Docs
#### 2) Insert the generated digest
Then the “Update a document” node inserts the agent’s final output into that newly created document:
* `documentURL: {{ $json.id }}` (the id returned from doc creation)
* `text: {{ $('AI Agent').item.json.output }}` AI in Global Ed News Google Docs
The connection chain is explicitly: **AI Agent → Google Docs (create) → Update a document (insert)**. AI in Global Ed News Google Docs
***
### The prompting pattern we used (and why it works)
This automation is basically two prompts with two different jobs:
1. **Research prompt (Perplexity):** “Be strict, recent, sourced, and structured.”
* hard date window (last 7 days)
* allowlisted domains only
* evidence table + links
* coverage priorities (UK → EU → US → Australia → China → global bodies)
2. **Writing prompt (Claude):** “Be readable, useful, and consistent, without inventing.”
* only use the brief’s facts/links
* interpret implications across the four HE impact areas
* fixed headings + SEO metadata
* explicit style rules (including “no em dashes”) AI in Global Ed News Google Docs
That separation is the whole trick: one model gathers and normalises evidence; the other turns it into a practitioner-facing narrative.
# Creating Infographics with Google's AI Suite
Creating infographics has never been easier with Google's Creative AI Suite.
## Using NanoBanana in Gemini
### **Step 1**
Go to [Gemini](https://gemini.google.com/app) and make sure you select the Image function. This will activate NanoBanana.
### Step 2
Provide Gemini either with a File from which to create the infographic, or with the text from which to create the Infographic followed by a prompt, such as :
```
// Create a square infographic from the attached documents. Make sure to focus specifically on the practical aspects of it and emphasize instructions.
```
### Step 3
Include additional information about your style, brand guidelines and audience. Include additional parameters such as:
```
// Make sure to use our brand colour theme as per the below:
Background: f7ebe8
Main text: 080a47
Other elements: fd6b00 , 009ffd, d90368
Ensure the style is minimalistic fit for education.
```
### Result
Ta-dah! Exactly what we needed. Although we might ask it to remove the references from the picture.
## Using Notebook LM
### Step 1
Go to [Notebook ML](https://notebooklm.google.com/) and upload a source. It can be a file, text, website link, YouTube Video, or a file from Google Drive.
### Step 2
Once you have loaded the resource click on the Edit Infographic Icon. Maje sure to click on the Icon, not the main Infographic button as if you do that Google will just automatically create one. By editing it you have more control over the format. Here you can choose a preferred orientation and add extra details.
```
// A practical infographic taking users through a how to journey. Make sure to use our brand guidelines:
Background: f7ebe8
Main text: 080a47
Other elements: fd6b00 , 009ffd, d90368
Ensure the style is minimalistic fit for education.
```
### Results
a) Without custom instructions (Google decide the style)
b) With custom instructions (You decide the style)
## Best Approach
You decide what works best for you and your use case. The beauty of this is you can tweak these instructions and refine them until you come up with the perfect recipe. Feel free to expriment with different types of illustrations - such as isometric, realistic, anime style, cartoon style, newspaper style, caricature style etc
# ReasonLens: Current Capabilities and Development Roadmap
ReasonLens is an AI Safety Audit Studio designed specifically for the education sector. The platform enables schools, universities, and education administrators to evaluate AI tools for safety, bias, and reliability before deployment, without requiring technical expertise. Built by AI For Global Education and powered by UniGlobal Technologies, the platform addresses critical governance challenges as AI tools proliferate across educational settings.
This report outlines the platform's current functionality and the planned qualitative improvements required before open-source release.
### Current Platform Capabilities
#### The Problem We Address
As AI tools proliferate in education (tutoring bots, writing assistants, research aids), institutions face critical governance challenges:
| Challenge | Risk |
| ------------------- | ------------------------------------------------------------------------------- |
| Hidden biases | AI may treat students differently based on gender, race, or cultural background |
| Harmful content | AI may generate inappropriate, violent, or sexual content |
| Academic integrity | AI may help students cheat or plagiarize |
| Privacy violations | AI may request or expose personal data |
| Misinformation | AI may present false information as fact |
| Mental health risks | AI may respond inappropriately to students in crisis |
ReasonLens addresses these challenges by providing automated, comprehensive safety audits that would take humans weeks to perform manually.
#### Three Layers of Protection
The platform combines three complementary audit approaches:
**Layer 1: Interaction Testing** An AI plays the student, probing the tool being tested with challenging scenarios. The tool doesn't know it's being tested. This uses PETRI (Parallel Exploration Tool for Risky Interactions), an open-source framework from Anthropic.
**Layer 2: Safety Screening** Automated checks for harmful, offensive, or inappropriate language using JailbreakTrigger and RealToxicityPrompts via Detoxify.
**Layer 3: Fairness and Accuracy** Bias detection using CrowS-Pairs benchmarks and factual reliability assessments using TruthfulQA.
#### Pre-Built Scenario Packs
The platform includes eight pre-built scenario packs designed for education contexts:
| Scenario | What It Tests |
| ---------------------------- | --------------------------------------------- |
| Intercultural Advisor | Cultural sensitivity and bias avoidance |
| GenAI Writing Mentor | Technical accuracy and citation integrity |
| Accessibility-First Teaching | Inclusive design and accessibility compliance |
| Privacy and Consent | Data protection and consent verification |
| Integrity Helpdesk | Academic integrity and appropriate refusals |
| + 3 additional packs | Various education-specific scenarios |
#### Report Outputs
The platform generates three types of outputs:
**Quick Briefing:** A one-page summary with Green/Yellow/Red status, top concerns, and recommended safeguards.
**Governance-Ready Reports:** Detailed PDF/Word exports suitable for board presentations, including visual data summaries, searchable conversation transcripts, and 37-dimension scoring breakdown.
**Actionable Recommendations:** Specific institutional controls with priority ranking.
#### Technology Foundation
ReasonLens is built on established open-source safety research:
* PETRI from Anthropic (interaction testing framework)
* Inspect AI from UK Government BEIS
* Detoxify (Apache 2.0 license) for toxicity analysis
* CrowS-Pairs and TruthfulQA benchmarks from HuggingFace
The platform infrastructure uses React 18 with TypeScript for the frontend, Supabase for backend services (database, authentication, edge functions), Modal for serverless compute, and integrations with OpenAI, Anthropic, and Google AI models.
***
### Minimum Qualitative Release Standard
Before publishing the Education AI Safety Toolkit openly, AIFGE will complete an initial set of qualitative uplift workstreams to ensure the methodology is education-relevant, fair, and suitable for broad reuse. The trustees propose completing the following three workstreams for the first release.
#### Workstream 1: Education-Sector Risk Taxonomy and Definitions
**Goal:** Establish a clear, education-specific risk taxonomy and consistent definitions so that scoring and interpretation are repeatable and meaningful.
**Deliverables:**
* AIFGE Education AI Risk Taxonomy (1-2 pages)
* Glossary and definitions, including what constitutes pass/fail or concern levels
* Examples of acceptable vs unacceptable outcomes for key dimensions
**Acceptance Criteria:**
* Definitions are understandable by non-technical education leaders
* Dimensions map clearly to common education governance concerns (safeguarding, privacy, fairness, integrity, reliability)
#### Workstream 2: Scenario Pack Quality Assurance
**Goal:** Ensure scenario packs are realistic, diverse, and do not introduce bias or inappropriate content in the test design itself.
**Deliverables:**
* Scenario QA checklist (coverage, realism, safeguarding boundaries, bias hygiene)
* A reviewed set of scenario packs with version notes and rationale for changes
* A process for proposing, reviewing, and approving future scenarios
**Acceptance Criteria:**
* Coverage across age ranges and key education contexts (school/FE/HE, SEND, EAL, safeguarding)
* Prompts are proportionate and avoid unnecessary explicit content while still testing real risks
* Each scenario pack includes purpose, intended risks tested, and any limitations
#### Workstream 3: Fairness and Inclusion Review (EDI Lens)
**Goal:** Ensure the Toolkit aligns with AIFGE's EDI commitments and supports detection of unfair or discriminatory outputs in education contexts.
**Deliverables:**
* Fairness and inclusion review checklist (education-specific)
* Bias-focused scenario additions or revisions, including intersectional considerations
* Guidance on interpreting bias signals and avoiding over-generalisation
**Acceptance Criteria:**
* Review explicitly considers protected characteristics and common education bias risks
* Toolkit guidance avoids stereotyping and supports culturally sensitive assessment
***
### Proposed Open Source Strategy
Following completion of the three workstreams, AIFGE recommends releasing an "Education AI Safety Toolkit" containing:
* Scenario pack definitions (JSON/YAML)
* The 37-dimension scoring rubric with education-focused interpretations
* Plain-language translation mappings
* Documentation on running PETRI with education scenarios
* Guidance on interpreting results
This approach:
* Positions AIFGE as a thought leader in education AI safety
* Encourages community contributions of new scenarios
* Creates an ecosystem where ReasonLens remains the premium, easy-to-use option
* Aligns with AIFGE's mission of making safety tools accessible globally
The complete React UI, user management, billing infrastructure, and custom integrations (such as Napkin AI) would remain proprietary as competitive differentiators.
# System Architecture
{% @mermaid/diagram content="graph TB
subgraph Frontend\["React Frontend"]
UI\[Landing Page & Dashboard]
RW\[Run Wizard]
RD\[Run Detail View]
RV\[Report Viewer]
end
```
subgraph Backend["Lovable Cloud Backend"]
DB[(Supabase Database)]
Auth[Authentication]
EF[Edge Functions]
end
subgraph Compute["Modal External Compute"]
PETRI[PETRI Engine]
TOX[Detoxify Toxicity]
BENCH[Benchmarks]
end
subgraph AI["AI Providers"]
OAI[OpenAI]
ANT[Anthropic]
GGL[Google]
end
UI --> RW
RW --> EF
EF --> DB
EF --> PETRI
PETRI --> OAI
PETRI --> ANT
PETRI --> GGL
PETRI --> TOX
PETRI --> BENCH
PETRI --> EF
EF --> RD
RD --> RV
Auth --> DB
```
" fullWidth="true" %}
# Three-Layer Audit Flow
{% @mermaid/diagram content="flowchart TD
Input\[AI Tool to Audit]
```
L1[Layer 1: Interaction Testing]:::section
P1[AI plays student]
P2[Tool responds naturally]
P3[Unaware of testing]
L2[Layer 2: Safety Screening]:::section
S1[JailbreakTrigger]
S2[RealToxicityPrompts]
S3[Harmful language detection]
L3[Layer 3: Fairness & Accuracy]:::section
F1[CrowS-Pairs bias test]
F2[TruthfulQA accuracy]
F3[Stereotype detection]
Output[Comprehensive Report]
Input --> L1
L1 --> P1 & P2 & P3
P1 & P2 & P3 --> L2
L2 --> S1 & S2 & S3
S1 & S2 & S3 --> L3
L3 --> F1 & F2 & F3
F1 & F2 & F3 --> Output
classDef section fill:#4a5568,color:#fff,font-weight:bold" fullWidth="true" %}
```
# User Journey
{% @mermaid/diagram content="flowchart TD
Setup:::section
S1\[Select AI tool to audit]
S2\[Choose scenario packs]
S3\[Configure parameters]
```
Execution:::section
E1[Launch audit]
E2[AI interactions run]
E3[Safety screening]
E4[Benchmark tests]
Results:::section
R1[View Quick Briefing]
R2[Explore transcripts]
R3[Download PDF report]
Action:::section
A1[Implement safeguards]
A2[Re-audit if needed]
Setup --> S1 --> S2 --> S3
S3 --> Execution --> E1 --> E2 --> E3 --> E4
E4 --> Results --> R1 --> R2 --> R3
R3 --> Action --> A1 --> A2
classDef section fill:#4a5568,color:#fff,font-weight:bold" fullWidth="false" %}
```
# Database Entity Relationship
{% @mermaid/diagram content="erDiagram
USERS ||--o{ RUNS : creates
RUNS ||--o{ TRANSCRIPTS : contains
RUNS ||--o{ REPORTS : generates
RUNS }o--|| SCENARIOS : uses
RUNS }o--|| MODELS : tests
```
USERS {
uuid id PK
string email
string role
}
RUNS {
uuid id PK
uuid user_id FK
string status
jsonb config
timestamp created_at
}
TRANSCRIPTS {
uuid id PK
uuid run_id FK
jsonb messages
jsonb scores
}
REPORTS {
uuid id PK
uuid run_id FK
text summary
jsonb data
}
SCENARIOS {
uuid id PK
string name
string category
text system_prompt
}
MODELS {
uuid id PK
string provider
string model_name
boolean active
}
```
" fullWidth="true" %}
