Building an Autonomous Engineering Org
summary
Claims a full conversion of an enterprise engineering org into an agentic one using internal agents like Goose and Claude Code plus Anthropic MCP design partnership, reaching 90% tool adoption, then achieving measurable impact: AI‑authored code +69%, reported time savings +37%, automated PRs ×21. Engineers build repo readiness assets and an orchestrator called Builder Bot backed by a 25,000 repo world model to reach stage five autonomy; it works technically but produces hard organizational consequences including layoffs.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:05AI enablement phases
- 2:28Agentic engineering org
- 3:30Maturity model for AI agents
- 5:38AI champions program
- 7:23Making repos AI ready
- 9:49Delegating to agents
- 12:38Results after 3 months
- 13:21Scaling with multi-agent parallelism
- 15:07Builder Bot orchestrator
- 16:52Reflecting on journey
related talks
24mBuilding an AI Native Engineering Org
27mAgentic Engineering: Working With AI, Not Just Using It
30mBuilding the Agentic Enterprise: Turning Data into Autonomous Business Systems
27mThe accidental AI revolution
46mAgentic Engineering: From Writing Code to Reviewing It
33mThe Autonomous Enterprise
26mOur Journey to Agentification
29mPairing with the machine: How AI Agents are rewriting the rules of software development