AI Under Control: accelerating safely
summary
Covers how current AI tools can speed software development but increase reliability risks and legacy code. Proposes a framework organizing approaches across specifications, code, tests, and context engineering to balance speed, reliability, and maintainability, and gives practical ideas teams can experiment with.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 1:49Speaker background
- 3:14AI technologies overview
- 5:20Using AI in development
- 7:26AI risks and limits
- 10:13Vibe coding pitfalls
- 12:41Vibe coding vs software engineering
- 13:02Controlling AI in production
- 17:35When to involve AI in projects
- 19:41Context engineering example
- 23:32Software craft best practices
- 25:17TDD and AI
- 27:41BDD and prompt engineering
- 28:45Mastering AI attitudes
- 31:56Key AI skills
- 34:05AI is here to stay
- 35:48Summary
related talks
19mAI in the trenches: Real-world wins without breaking things
37mAI-assisted development: Common pitfalls and smarter practices
39mAI-assisted development: Common pitfalls and smarter practices
18mHumans + AI: The Future of Software Development Teams
01mAI Is Changing How We Developer Software!
46mMaking AI Adoption Work: A Practical Structure for Modern Software Development
44mThe Future of Engineering Teams in an AI-Native World
24mAI Governance for developers: A practical framework for deploying autonomous coding agents safely…
