Design Thinking: Generative AI Style
summary
An agent pair automates design thinking by turning user requirements into technical epics and then into starter stories: a product‑owner design‑thinker agent produces high‑level epics and a scrum‑master agent generates 3–5 user stories per epic with acceptance criteria. A three‑day manual workshop previously yielded ~2–3 epics with ~5 stories each; the agents produce coherent equivalents in seconds, running locally on a MacBook Pro M1 Max with 32 GB using open‑source LLMs and LangChain‑style tooling. A pilot for a steel yard (drone QR scans updating SAP) validates the workflow end to end.
AI-written summary · about
chapters (9)
- 0:00Introduction to design thinking
- 1:46Four pillars explained
- 4:20Why design thinking matters
- 8:15Design thinking and agile
- 12:07AI agents for design thinking
- 16:02Business context of demo
- 25:14Live demo: AI agents generate epics
- 36:55Wrap-up and key takeaways from the session
- 39:22Q&A
related talks
43mDesign Thinking: Generative AI Style
21mDesigning in the age of the 10x engineer
19mBeyond agents: AI as a creative partner
34mDesign in the times of AI
33mBuilding an Agentic Design System
11mStoryEnsemble: Enabling Dynamic Exploration & Iteration in the Design Process with AI and Forward...
20mAI will upend your process—for the better
30mUsing AI to Create Better Requirements and Designs