# Build a Slack knowledge graph with Claude and Neo4j: n8n workflow

> Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Claude.

Source: https://millionrounds.com/workflow/build-a-slack-knowledge-graph-with-claude-and-neo4j (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [AI assistants](https://millionrounds.com/workflows?category=AI+assistants#library)

# Build a Slack knowledge graph with Claude and Neo4j

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to Claude. 18 steps, 2 loops or waits: a working afternoon to understand properly.

Medium Calls a model: Claude

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-slack-knowledge-graph-with-claude-and-neo4j)

**18 steps** Medium: a working afternoon

**0** Branches: places the flow splits

**2** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 3 Model 4 Logic 9 Service 2

The steps in the order they run, from what starts it.

- 1 **Webhook - Chat Message Ingest** Webhook *Starts it*
- 2 **Schedule - Poll Slack Every 15 min** Schedule trigger *Starts it*
- 3 **Anthropic Claude - Entity Extractor Model** Lm Chat Anthropic *Model*
- 4 **Anthropic Claude - Relationship Enricher Model** Lm Chat Anthropic *Model*
- 5 **Normalise Message Payload** Set *Logic*
- 6 **AI - Entity & Relationship Extractor** Agent *Model*
- 7 **AI - Relationship Enrichment & Weighting** Agent *Model*
- 8 **Python - Noise Filter & Signal Tagging** Code *Logic*
- 9 **JS - Merge & Structure Knowledge Graph** Code *Logic*
- 10 **Filter - Keep Relevant Messages Only** Filter *Logic*
- 11 **Wait For Data** Wait *Logic*
- 12 **Wait - API Rate Limit Buffer** Wait *Logic*
- 13 **JS - Validate Graph Integrity** Code *Logic*
- 14 **Filter - Valid Graphs Only** Filter *Logic*
- 15 **Neo4j - Upsert Nodes & Edges** Http Request *Service*
- 16 **Google Sheets - Append Audit Log Row** Http Request *Service*
- 17 **JS - Build Success Response** Code *Logic*
- 18 **Webhook Response - 200 OK** Respond To Webhook *Starts it*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 18, 2 loops or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** Claude

## Questions

What does it need to run?

An n8n account, and a key for Claude. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Claude. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 18 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 18 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-slack-knowledge-graph-with-claude-and-neo4j)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also ai assistants, with the same services where possible, closest in size first.

- [**AI-powered email forwarding to WhatsApp with Gmail and Outlook** 18 steps · calls a model · Gmail](https://millionrounds.com/workflow/ai-powered-email-forwarding-to-whatsapp-with-gmail-and-outlo)
- [**Answer restaurant voice queries with ElevenLabs and OpenAI** 18 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/answer-restaurant-voice-queries-with-elevenlabs-and-openai)
- [**Automate Gmail Organization** 18 steps · calls a model · WordPress](https://millionrounds.com/workflow/automate-gmail-organization)
- [**Build an advanced multi-query RAG system with Supabase** 18 steps · calls a model · Supabase vectors](https://millionrounds.com/workflow/build-an-advanced-multi-query-rag-system-with-supabase)
- [**Clear integration of GPT-4 with OpenAI** 18 steps · calls a model](https://millionrounds.com/workflow/clear-integration-of-gpt-4-with-openai)
- [**Create AI-generated books with OpenAI and DALL-E** 18 steps · calls a model · Google Drive, S3](https://millionrounds.com/workflow/create-ai-generated-books-with-openai-and-dall-e)