All sessions
Agentic EngineeringSession
DeepSWE: expert code datasets
Serena Ge
- When
- Thursday, July 210:45 AM – 11:05 AM · 20 min
- Where
- Track 8San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
DeepSWE and the data/eval layer behind coding agents; why curated expert code datasets matter for reliable agent performance.
Speaker
Serena Ge
CEO, Datacurve
CEO at Datacurve. Building research and data collection infrastructure to advance frontier models. Datacurve is the creator of DeepSWE benchmark - the benchmark designed to reflect the realistic experience of developers in their day-to-day work.
More in Agentic Engineering
- MCPs, CLIs, and Skills: Choosing the Right Tooling Layer for Agentic DevelopmentThursday, July 2 · 11:10 AM – 11:30 AM · Main Stage
- Anthropic's CCA Exam as a Field-Guide for Agentic EngineeringThursday, July 2 · 11:10 AM – 11:30 AM · Track 8
- Auth for Agents: Unblock Autonomous AI with auth.mdThursday, July 2 · 11:40 AM – 12:00 PM · Main Stage
- Guide, Verify, Solve: The Engineering Discipline Agentic Development DemandsThursday, July 2 · 11:40 AM – 12:00 PM · Track 8
- Benchmarking Coding Agents on New vs Legacy Code basesThursday, July 2 · 12:05 PM – 12:25 PM · Track 8
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.