Mentoring the Machine
summary
Claims that AI agents can turn weeks of work into hours are backed here by concrete results: an Augment Extension agent finds and reverts a bad commit across 12 services and 20,000 lines, runs tests, and drafts a postmortem, converting a three‑week gRPC upgrade into half a day of human keyboard time. The workflow uses a context engine, Slackbot, memories for shared knowledge, and MCP/native integrations, plus three adoption steps—knowledge gathering, tool familiarity, and leaning in—and ships remote agents as a product feature.
AI-written summary · about
chapters (8)
- 0:00Introduction to mentoring AI
- 2:53Chaotic Tuesday scenario
- 5:20AI handling emergencies
- 8:52Mentoring AI like juniors
- 10:38Scaling AI across teams
- 12:28Building knowledge infrastructure
- 14:56Future of AI-driven development
- 18:45Conclusion and call to action
related talks
27mAgentic Engineering: Working With AI, Not Just Using It
27mEngineering in the Age of AI: Making AI Work for Us, Not Replace Us
46mRecalibrate - How AI shakes up software team
29mPairing with the machine: How AI Agents are rewriting the rules of software development
27mSoftware engineering with GenAI
52mCut the Hype and Build Your Own AI Agents
40mHuman Centric Software Development Augmented by AI
16mCoding Reinvented How AI Agents Are Shaping the Future of Software Development