Build Daily

Tinley Park · October 13, 2026
Neo4jOct 12, 2026

IBM WatsonX Orchestrate Neo4j Integration Demo

Open on YouTube ↗← Back to the feed
What it covers

This demo walks through building an AI agent that combines Neo4j's knowledge graph with IBM watsonx Orchestrate to deliver accurate, context-aware answers via natural-language queries. It covers using MCP tools and custom Python functions, deploying the agent to Slack or embedding it in applications, and points to the open-source integration on GitHub.

The outline

Every point the video makes, in the order it makes them.

  1. 01

    Agent Architecture

    The video demonstrates how to build an AI agent powered by Neo4j and IBM watsonx Orchestrate.

  2. 02

    Knowledge Graph for Context

    A Neo4j Knowledge Graph is used to ground the agent's responses in accurate, context-aware information.

  3. 03

    MCP Tools & Custom Functions

    Standard MCP tools and custom Python functions enable natural-language database queries and investment insights with transparent tool execution.

  4. 04

    Infrastructure-Free MCP

    The integration eliminates the need to manage MCP server infrastructure yourself.

  5. 05

    Deployment & Embedding

    The finished agent can be deployed to Slack or embedded directly into your own applications.

  6. 06

    Open-Source Repository

    The integration is available as open source in the Neo4j Agent Integration GitHub repository for further exploration.

Graph memory, no team

A plain-English agent over a Neo4j knowledge graph, wired through MCP tools and an open-weight model, with the whole integration open-sourced on GitHub. For a solo builder, that makes structured, context-aware memory a composable layer rather than a from-scratch pipeline. The Slack deployment path keeps distribution simple: ship the agent where people already work.