Human Centric Software Development Augmented by AI
summary
Six-month engagement embeds AI agents into a microservice‑heavy legacy codebase, investing about one month to enable local dev, deterministic repos and trunk-based development before AI can run. Workflow puts automated test first so AI generates automated end-to-end tests and code against CI; result: much faster output but lower code quality and rising cognitive debt. Teams regain progress only after architecture workshops, tighter feedback loops and preserving knowledge in tests — partial success with clear tradeoffs.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 2:09Human-centric AI approach
- 3:57AI-augmented development
- 15:01Jidoka and automated testing
- 26:27AI-assisted development setup
- 34:00Progress to feedback focus
- 38:44AI as commodity and closing
related talks
23mHuman-Centered AI: Supporting, Not Replacing, Frontend Developers
18mHumans + AI: The Future of Software Development Teams
27mEngineering in the Age of AI: Making AI Work for Us, Not Replace Us
01mAI Is Changing How We Developer Software!
27mAgentic Engineering: Working With AI, Not Just Using It
27mAI-First Software Maintenance & AI-First Software Delivery
18mLeveraging AI to Improve the Developer Experience
37mThe Augmented Engineer: Evolving Sensible Defaults through Human-Centric AI