OpenClaw feels like it's learning: it discovers capabilities, stitches tools together, builds solutions it wasn't explicitly taught. The reality is simpler — it's an LLM calling tools in a loop, powered by Pi, a minimal coding agent SDK. This talk is about what you can build once you understand that.

Matthias Luebken walks through embedding Pi in a real product: a B2B sales pipeline where incoming RFP emails route to customer-specific agent sessions, CLIs expose CRM and ERP data in a form the agent can use cleanly, and the only output a human sees is a draft in their inbox. The architectural principle running through it: don't fight the coding agent, make things easy for it. Design your data access and tool interfaces so the agent can work naturally rather than having to compensate for complexity.

Speaker info:
- https://x.com/luebken
-https://github.com/luebken

AI Engineer

A conference talk exploring how to embed the OpenClaw coding agent (built on the Pi framework) into real products. The speaker walks through Pi's agent core architecture — an LLM running tools in a loop — and demonstrates how to extend it with custom tools, session management, UI interactions, and event hooks using TypeScript. A real-world example shows a sales automation system where per-customer agents monitor email inboxes, route requests for proposals, call CRM/ERP tools via CLIs, and generate draft email responses. Key takeaways: coding agents are becoming core software building blocks, Pi is minimal and ideal for experimentation, and the emerging pattern is making systems easy for agents to access.

A Piece of Pi: Embedding The OpenClaw Coding Agent In Your Product — Matthias Luebken, Tavon