Build Without Limits - Lessons Learned Working with Data and AI Coding Assistants
summary
Over the last 12 months of hands‑on use the claim is concrete: generative assistants speed prototyping, debugging and SQL work but they hallucinate without strict context and guardrails. The talk shows three emerging patterns (exploration, learning, productivity), demos using Kira CLI and MCPs like model context protocol, and concrete wins — faster schema inference, automated DAG modernisation, and query debugging — plus failures: generated queries often fail load tests unless schema and examples are provided.
AI-written summary · about
chapters (9)
- 0:00AI coding assistants intro
- 2:31Emerging AI use cases
- 4:36Data project foundations
- 10:14Data formats and samples
- 15:34SQL tasks simplified
- 23:46Refactoring data systems
- 26:56Production data optimization
- 28:42AI data work considerations
- 30:25Q&A
related talks
39mBuild without limits: lessons learned from using generative AI dev tool
47mLessons learned from using generative AI dev tools
37mGenerative AI: Beyond (Just) Hype
26mAl and Software: The Good, The Bad, The Scary
13mMeet the Speakers
25mYour AI Needs an Assistant
41mGenerative AI: bliss or miss?
58mAI, Determinism, Code Generation and Refactoring