All templates
Multi-Agent#LLM#Multi-Step#Content#Newsletter#Multi-Agent

Research Brief → Draft Writer

Two-stage pipeline: one LLM pulls facts and bullets, the next turns them into a polished paragraph for blogs or newsletters.

Research Brief → Draft Writer

A compact multi-step AI layout: Research compresses sources into bullets, Writer produces publish-ready copy. Great for newsletters, changelog blurbs, and founder updates.

What this workflow does

  1. Input sets the topic or pasted article URL context
  2. LLM (Research) returns concise bullet facts (neutral tone)
  3. LLM (Writer) rewrites into a short article paragraph
  4. Output surfaces the draft text

Use cases

  • Weekly team digests
  • Turning long threads into LinkedIn posts
  • Teaching sequential LLM patterns before jumping to Agents

Setup

Add model credentials on both LLM nodes. Tune temperature: lower for Research, slightly higher for Writer.

FAQ

Is this "multi-agent"? It's a sequential multi-LLM pipeline — easy to extend with Tool or Agent nodes later.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3Press Cmd+V / Ctrl+V — nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
#LLM#Multi-Step#Content#Newsletter#Multi-Agent

Click a node to select it — same as the Heym editor; the panel shows its settings.

5 nodes · Free & source-available

Explore related automations — each page links to other templates so you can discover more use cases.

Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym