How Agentic AI Empowers Creative Thinking
summary
Argues that agentic AI plus a knowledge graph and Model Context Protocol (MCP) shifts prototypes into near‑production features by supplying a curated context to agents. Shows a working flow: prototypes from cloud/cursor/codex hit a graph fed from Figma, Storybook, Jira and YAML component manifests, generate code close to mergeable, and return validation warnings during PRs. Implementation is hybrid: extract skeleton from code, iterate with humans; syncing remains a work in progress.
AI-written summary · about
chapters (9)
- 0:00Introduction and context
- 2:08AI-assisted prototyping
- 4:42Overcoming vibecoding pitfalls
- 7:03The prototype lifecycle
- 8:34Curated context for AI
- 11:05Implementing knowledge graphs
- 14:21Graph-based integration
- 17:53Future of generative UI
- 20:21Takeaways and Q&A
related talks
19mBeyond agents: AI as a creative partner
27mAgentic Engineering: Working With AI, Not Just Using It
20mReimagining InnerSource for the Agentic AI Era
32mFigma deep dive: Agentic workflows and the MCP
27mEmerging Patterns Agentic AI
29mPairing with the machine: How AI Agents are rewriting the rules of software development
22mAgentic AI for Engineering Leaders | Strategy & Execution Guide
30mKeynote: Fireside Chat