The Plan That Learns
summary
AI agents triage hundreds of emerging traffic patterns down to a handful that need human time, enabling action inside narrow buy windows (weeks down to minutes) and turning a weeks‑long choice process into hours not weeks. Agents that reason across conflicting sources move from ~30% to 80%+ accuracy after measure‑enrich‑regrade eval loops, and choices are presented as a ranked, costed menu with decision traces so past human moves can be measured and compounded.
AI-written summary · about
related talks
08mReal AI Agents Need Planning, Not Just Prompting
34mAI Agents: Transforming Autonomous Decision-Making
24mPut On Your AI-Colored Glasses
45mAI agents in practice - beyond the prototype
28mAI Agents Driving Product Decisions | AI for Product Strategy
26mDesigning Anticipated User Experiences
32mFrom Three Days to One Minute: Architecture Trade-offs in Production Enterprise AI
39mAI as a Catalyst, Not a Replacement