Autoresearch in the wild
Roland Gavrilescu, Julian Bright
- When
- Wednesday, July 13:20 PM – 3:40 PM · 20 min
- Where
- Main StageSan Francisco, CA · imported from ai.engineer's public schedule feed
About this session
We have reached model capability overhang. Models are now bottleneck by the systems built around them. In this session we discuss how the next generation of compound AI systems need to be designed for self-improvement, how to set up feedback loops that automate the continuous refinement of the end-to-end architecture.
Speakers (2)
Co-Founder, CEO, Introspection
Co-founder and CEO at Introspection, building infra for self-improving AI systems. Previously at xAI and Superhuman.
Co-Founder, Introspection
Julian Bright is a co-founder at Introspection, building infrastructure for agent autoresearch and agent systems with Roland Gavrilescu.
More in Autoresearch
- Field Guide to FableWednesday, July 1 · 9:05 AM – 9:25 AM · Main Stage
- Perception AgentsWednesday, July 1 · 9:45 AM – 10:05 AM · Main Stage
- Research to Reality with Google DeepMindWednesday, July 1 · 10:05 AM – 10:25 AM · Main Stage
- Evals Track IntroWednesday, July 1 · 10:25 AM – 10:30 AM · Main Stage
- First Steps Toward Automated AI ResearchWednesday, July 1 · 10:45 AM – 11:05 AM · Main Stage
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.