Kenote: AI Didn’t Replace You. It Promoted You!
summary
Argues that engineers move from coding to system design and control, showing concrete practices: use agents.md to store curated project memory (keep entries small, ~300 lines), run long-running automation with Copilot CLI to fix flaky tests and profiling, use plan mode then generate code, and gate agents with human-in-loop approvals and restricted permissions. Notes token limits (examples: 160k vs 1M windows), danger above ~65% context causing hallucinations, recommends red green TDD trigger for autonomous bug fixes, and cites measured 30% productivity gains.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 2:43AI agent workshops insights
- 10:10AI conversation context
- 20:21AI agent tooling
- 30:22Autonomous AI agents
- 41:39Feedback loops strategies
- 51:16Strategic AI adoption
- 56:00Key takeaways
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
26mAI Agents as Your Co-Developer
29mPairing with the machine: How AI Agents are rewriting the rules of software development
37mThe Augmented Engineer: Evolving Sensible Defaults through Human-Centric AI
35mAI Agent and the Promotion You Didn't Ask For
01h 02m10 Tips To Level Up Your AI-Assisted Coding
46mRecalibrate - How AI shakes up software team