FeaturedAI Agents#AI#Research#Supabase#Markdown#Archive

AI Research Brief Supabase Archive

Turn research notes into a structured AI brief and save the finished Markdown in Supabase.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#AI#Research#Supabase#Markdown#Archive

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

5 nodes · Free & source-available

AI Research Brief Supabase Archive

Turn rough research notes into a useful, shareable brief and keep the finished Markdown in Supabase. The workflow is a normal workflow template: an LLM writes the brief, a Set node builds a database-ready record, and Supabase stores it for later retrieval.

What this workflow does

  1. ResearchInput accepts a topic and supporting notes
  2. WriteResearchBrief produces a concise Markdown brief with findings, evidence, and open questions
  3. BuildResearchRecord maps the topic and brief into database-ready fields
  4. SaveResearchBrief inserts the record into Supabase
  5. ArchiveResult returns the write result

Use cases

  • Competitive research summaries
  • Internal product discovery briefs
  • Reusable AI research notes for a Supabase-backed knowledge archive

Setup

Create a Supabase credential and choose it on SaveResearchBrief. Create a research_briefs table with fields such as topic, brief_markdown, and brief_state, or update the table name and Set mappings for your schema. Add an LLM credential to WriteResearchBrief, then replace the topic and notes with your own source data.

Notes

This is a standard workflow, not a dashboard widget. The generated Markdown is saved as text in your own Supabase table, so you can query, review, or extend the archive in later workflows.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
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