Why AI needs GraphQL
summary
Argues that foundation LLMs need a single universal GraphQL API to bridge imprecise language and precise enterprise facts, shows a trained model that introspects a StepZen endpoint (now part of IBM), generates GraphQL queries that call CRM, FedEx tracking and OpenWeather, returns JSON and a second model converts it to English, and demonstrates RAG against a Milvus vector DB for developer assistants. The live demos work and reveal on‑the‑fly wiring and schema curation needs.
AI-written summary · about
chapters (12)
- 0:00Introduction and welcome
- 1:25GraphQL vs REST debate
- 3:55AI needs enterprise data
- 6:21GraphQL as connective tissue
- 8:30Dynamic GraphQL circuits
- 12:41Training LLMs with GraphQL
- 13:01Live demo with Watson
- 16:41Schema design for AI
- 19:13Architecting for AI traffic
- 23:47AI loves GraphQL developers
- 27:18RAG pattern demo
- 30:46Conclusion and call to action
related talks
14mKeynote: GraphQL in the AI Era
01h 00mWorkshop: Getting Data Ready for AI - With Unified GraphQL &SQL Endpoints
27mAI, SQL, and GraphQL Walk into a Fertility Clinic
17mThe year ahead for GraphQL Federation: Combining APIs for the AI era.
29mAI, SQL, and GraphQL Walk into a Fertility Clinic… LLM-based Medical feature development
24mFrom Query to Conversation: GraphQL as an AI Interface Layer
21mKeynote: How GraphQL is Redefining API Orchestration for the AI Era
26mEvolving GraphQL: Designing APIs That Deliver Insights with Intelligent Resolv…