The Future is Malleable
summary
Claim: combining large language models with schema-aware Graph APIs produces user-driven, malleable apps. Prototype wires a prompt to the app schema and returns runnable GraphQL queries via a simple malleable() API, generating a live name and ID table from plain English and demonstrating that the approach works really well in demos. References include browser extensions (Wildcard), workspace builders (Koda, Notion, Pol), Solid pods and Webstate for data ownership, and Dynamicland for composable UX.
AI-written summary · about
chapters (9)
- 0:00Introduction and welcome
- 1:10Problem with predefined apps
- 3:41What are malleable applications
- 7:54AI empowering non-technical users
- 12:11Software as playgrounds
- 15:25API layer for customization
- 18:17Building malleable apps step by step
- 22:11Malleable software projects
- 26:33Future of malleable software
related talks
25mAI, GraphQL, and the Rise of Malleable Applications
47mSchema Design in the Age of AI: Pragmatic Patterns to Evolve and Ship Fast
29mClosing the Loop: How GraphQL Gives Coding Agents Eyes on What Actually Matters
35mDynamic, Safe Ops Using AI to Generate Trusted Operations from Text Prompts
27mHow GraphQL Gives Coding Agents Eyes on What Actually Matters
21mKeynote: How GraphQL is Redefining API Orchestration for the AI Era
31mA GraphQL-inspired Orchestration Language for the AI Era
31mGraphQL Embeddings: AI-Powered Dynamic Operations From Schema To IDE