What to look forward to
This hands-on workshop will show how to build evals that uncover agent failures, run them in Modal’s serverless sandboxes, and use Braintrust’s observability platform to inspect traces and improve agent quality. Braintrust, an observability platform for agents, and Modal, a platform for production AI, will lead the session.
Inside the event
Join this workshop for a step by step guide to building evals and investigating agent traces inside Modal sandboxes with Braintrust's observability platform.
This is a hands-on workshop. Bring your laptop.
You'll learn
- How to build evals that identify agent failures
- How to run evals on Modal's serverless sandboxes
- How to continuously measure and improve agent quality with Braintrust
Agenda
6:00 PM Registration
6:30 PM Intro from Braintrust & Modal
7:00 PM Hands-on workshop
8:30 PM Drinks and canapés
About the hosts
Braintrust: the active observability platform for agents.
Modal: the platform for production AI
x+why One Great Cumberland Place
x+why One Great Cumberland Place, 1 Great Cumberland Pl, London W1H 7AL, UK. Confirm the venue with the organizer before traveling.
Open in Google Maps ↗Discovered through Cerebral Valley. Details come from the event listing and the organizer page; registration is managed by the organizer.
Last checked: Nov 4, 2026. Confirm current availability before making plans.
Organizer page checked: Nov 4, 2026. Check registration for the latest details.