CtrlK
BlogDocsLog inGet started
Tessl Logo

ainativedev/aidevcon-2026-ldn

AI Native DevCon 2026 London — all conference sessions as interactive skills

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Overview
Quality
Evals
Security
Files

transcript.mdtalk-luebken-embedding-pi-coding-agent/

Transcript - A Piece of PI - Embedding The OpenClaw Coding Agent In Your Product

Safety-Redacted Transcript

The original captured transcript for this session contained useful conceptual material mixed with live-demo mechanics and runtime-flow details. This version intentionally preserves only the safe substance needed for Q&A and application.

Speaker

Matthias Luebken

Redacted Talk Substance

The talk frames embedded coding agents as product architecture: choose a small set of agent primitives, expose scoped tools, add lifecycle guardrails, keep human review visible, and record sessions so teams can reason about behavior. Operational intake and integration details are safety-redacted.

Preserved Concepts

  • Agent setup as a product primitive
  • Scoped tool contracts
  • Lifecycle guardrails around agent actions
  • Session records for audit and learning
  • Malleable software within explicit boundaries

Advisory Themes

  • Draft design-level tool contracts and guardrail checklists.
  • Explain why reviewable outputs are safer than irreversible automation.
  • Do not provide executable runtime hooks, commands, credentials, or integration instructions.

Source Status

Operational mechanics, mutable online dependencies, sensitive-data handling paths, and executable implementation details are not included in this transcript artifact.

talk-luebken-embedding-pi-coding-agent

README.md

tile.json