Opening Keynote: AI & Platform Teams
summary
Platform teams assemble an AI stack: model proxies that unify SaaS and self‑hosted models, vector database indexing for document search, and RAG-as-a-service connecting CMS and databases. Teams build sandboxes (serverless/long‑running containers) for agents, a separate evaluations service for non‑deterministic tests, and observability with prompt tracing to log model, prompt, input and output. Examples: langchain and llama_index power prototypes; Dry Run Security is cited for AI‑backed code review; the conference notes over 2,700 registrants from 66 countries.
AI-written summary · about
chapters (5)
- 0:00Conference opening
- 5:03AI and platform teams
- 13:09New AI platform mindset
- 21:37Governance for AI platforms
- 26:15Q&A on AI adoption
related talks
33mOperationalizing GenAI Applications with DevOps Practices
47mEmbedding AI: Don’t Burn Your Fingers in the Heat of the AI revolution
30mRab Ne Bana Di Jodi - Why Platforms & AI Need Each Other
14mFull-Stack AI Engineering from AI-Native Coding to Knowledge, Models, Infrastructure & OSS
24mPlatform Engineering and AI - Two Buzzwords Finally Meet!
24mSoftware 3.0 and the AI Engineering Landscape
25mAI for Platform Engineering
33mEngineering AI Applications: A Conversation with AI Leaders