Sponsor talks on durable agent runtimes, fault-tolerant training, edge-native agents, and inference performance.
Accessible with the Expo Explorer pass and above.
Agents are starting to debug and improve themselves: production traces become evals, evals propose PRs, and PRs are tested against datasets before they ship. Langfuse co-founder, Marc, will live-demo this loop in Langfuse. He'll make the case that the infrastructure underlying this powerful loop should be open-source.
To be announced.