Keynote: The Common Pathway of AI and Software
summary
Argues that treating AI as an engineering pipeline produces pragmatic software results: a tested chain of planning module, knowledge retriever, and code generator turns vague prompts into reproducible commits. Uses models as developer assistants and measures failure modes—models often miss unstated requirements until a planning step clarifies intent. Demonstrates on real repos at poolside, where automated edits produce working patches within minutes and reduce manual iteration and surprise rollbacks.
AI-written summary · about
chapters (6)
- 0:00Welcome
- 2:53AI and software boundaries
- 4:10Software generation pipeline
- 8:41Focus on software
- 11:24Testing with developer questions
- 13:57Closing thoughts
related talks
30mKeynote: Fireside Chat
14mFull-Stack AI Engineering from AI-Native Coding to Knowledge, Models, Infrastructure & OSS
46mIntelligence as Infrastructure: What Developers Must Learn to Build with AI
26mBeyond the code: Leading engineering teams in the GenAI era
13mMeet the Speakers
05mKeynote: How Open Protocols Unleash AI’s Next Wave of Creativity and Impact
52mAI Is Just Software, What Could Possibly Go Wrong?
39mAI and the Democratization of Software Development