A GraphQL-inspired Orchestration Language for the AI Era
summary
A GraphQL-like language prototype keeps GraphQL’s typing and field selection but adds an extended selection set with expressions and reshaping, explicit entity references that let queries follow IDs across different APIs, a query keyword to call non‑GraphQL endpoints, and runtime type assertions at API boundaries. It targets agent‑generated orchestration, supports batched cross-service calls, offers explicit null/error handling, and prototypes action orchestration with recovery/compensation — experimental but runnable and designed to be checkable.
AI-written summary · about
chapters (7)
- 0:00Introduction and motivation
- 7:50Limitations of GraphQL for agents
- 10:38Extending GraphQL selection sets
- 16:17Entity references and navigation
- 21:33Handling mutations and workflows
- 23:19Flexible graph orchestration
- 25:27Q&A session
related talks
21mKeynote: How GraphQL is Redefining API Orchestration for the AI Era
47mSchema Design in the Age of AI: Pragmatic Patterns to Evolve and Ship Fast
25mAI, GraphQL, and the Rise of Malleable Applications
11mSponsored Keynote: GraphQL, BFFs and AI
26mJust Ask: Building a Natural Language GraphQL Agent from the Graph You Already…
16mIntro to GraphQL
27mThe Future is Malleable
35mDynamic, Safe Ops Using AI to Generate Trusted Operations from Text Prompts