Ctrlk
For the complete documentation index, see llms.txt. This page is also available as Markdown.

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

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

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.

PreviousClaude Code CookbookNextCreating Infographics with Google's AI Suite

Last updated