What to look forward to
This AI Engineering event will explore the infrastructure behind reliable, long-running agents, from forkable sandboxes and production-ready integrations to practical evaluations and episodic memory. Talks will feature experts from Daytona, Crusoe, Nango, and Langfuse, including a principal events manager, developer relations leaders, and a startup co-founder and CEO.
Inside the event
An event dedicated to exploring all things AI Engineering! Event partner: Brex ๐ 5:30 pm โ 6:00 pm Welcome and Opening Remarks ๐ค Marijan Cipcic, Principal Events Manager at Daytona ๐ 6:00 pm โ 6:10 pm Talk "Forkable Sandboxes for Long-Running Agents" ๐ค Muhammad Annas Hashmi, DevRel at Daytona Outline: Agents are starting to do real software work: installing dependencies, editing files, running tests, starting servers, and debugging over long sessions. But most AI systems still treat each run like a disposable prompt-response loop. That breaks down once the useful state lives not just in tokens, but in the actual machine. This talk is about the runtime layer agents need to become reliable builders. Iโll show how forkable Daytona sandboxes let you pause at important moments in an agent run, branch the environment, and sample multiple continuations from the same machine state. For builders, this turns long-running agent workflows into something you can inspect, compare, recover, and eventually optimize. ๐ 6:10 pm โ 6:20 pm Talk "TBA" ๐ค Connor Guerrero, Sr. Developer Relations Manager at Crusoe Outline: TBA ๐ 6:20 pm โ 6:30 pm Talk "Building production-ready agent integrations" ๐ค Bastien Beurier, co-founder and CEO at Nango Outline: Connecting an agent to an API is easy. Making it work across real users, accounts, and permissions is harder. Iโll share a practical playbook for agent connectivity across three main dimensions: coverage, reliability, and governance. Weโve used this playbook to power integrations for teams like Replit, Mastra, and ServiceNow. ๐ 6:30 pm โ 6:40 pm Talk "Good evals are boring" ๐ค Lotte Verheyden, Developer Relations Engineer at Langfuse Outline: Long-running agents fail in ways that are hard to spot, and with traces alone this becomes tedious to monitor. This talk covers how to turn traces into evals that serve you in improving your agent's execution quality. ๐ 6:40 pm โ 6:50 pm Talk "How to Build Truly Episodic Memory for Your Agent"
Meet in San Francisco, CA
City view. The source has not supplied a venue; check the organizer for the exact location.
Open in Google Maps โDetails come from the event listing; registration is managed by the organizer.
Last checked: Nov 18, 2026. Confirm current availability before making plans.