Understanding is the new bottleneck
Geoffrey Litt
- When
- Wednesday, July 110:45 AM – 11:05 AM · 20 min
- Where
- Track 6San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
Autonomous loops are hot, but the reality is that most agentic tasks still require human judgement. And to guide your agents well, it's not enough to just verify correctness -- you actually need to understand the work they're doing.
In this talk, I'll share some techniques for staying in the loop and efficiently developing understanding, combining old ideas from education and cognitive science with modern agent capabilities. You'll walk away with some practical tips for moving faster with agents by understanding more, not less.
Speaker
Design Engineer, Notion
Design Engineer at Notion. Building malleable software with AI. Previously research at MIT / Ink & Switch.
More in Design Engineering
- The Spatial Harness: Bringing Agents to the CanvasWednesday, July 1 · 11:10 AM – 11:30 AM · Track 6
- The Design-Code Roundtrip That Isn'tWednesday, July 1 · 11:40 AM – 12:00 PM · Track 6
- Mousepower: agents that can’t be measured, can’t be managed.Wednesday, July 1 · 12:05 PM – 12:25 PM · Track 6
- Design at the Speed of AdjectivesWednesday, July 1 · 1:30 PM – 1:50 PM · Track 6
- Training TasteWednesday, July 1 · 1:55 PM – 2:15 PM · Track 6
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.