Data Strategy for Generative AI Applications — Why Your Data is the Differentiator
summary
Generative AI projects succeed or fail on concrete data choices: the talk shows a travel-agency demo using text-to-SQL for relational profiles, semantic search with embeddings stored in a vector database, and RAG to fuse changing flight/pricing data instead of re‑fine‑tuning. It cites context windows up to 32k–200k tokens, flags data quality as the top C‑suite concern, and recommends tooling patterns like fine-tuning when knowledge is static and libraries (e.g. LangChain) or Bedrock for agents when live API actions are required.
AI-written summary · about
chapters (5)
- 0:00Introduction to data strategy
- 7:51Generative AI lifecycle
- 13:27Building a data strategy
- 19:08Leveraging data for GenAI
- 39:05Q&A and closing
related talks
34mGenerative AI Landscape Building a Modern Data Strategy
18mAccelerate generative AI development with integrated data platforms
18mNavigating the growth frontiers of generative AI
15mHarnessing the Power of Generative AI for Intelligent Applications
20mBeyond the Buzz: Discovering High-Impact Use Cases in the Generative AI Era
48mHow to Make Smart Architecture Decisions when Building Gen AI Apps
28mImproving responses in generative AI applications
22mGenerative AI - A Pragmatic Business View