Olmo Maldonado

Teams running AI applications in production generate thousands of traces a day, but can't read them all. Braintrust is launching Topics to automatically group traces into meaningful patterns, so you can see what's actually happening. Topics is accessible directly in the platform, so you're not relying on static reports. Build better datasets, generate inputs to your evals, and understand when new problems show up in production.

Observability tells you what happened. Evals tell you whether it's getting better. Braintrust connects the two by automatically surfacing patterns and acting on them. New from the Trace keynote: - Topics finds insights and errors - Loop enables human-powered remediation - Braintrust Gateway standardizes access and observability across model providers - Braintrust CLI brings the UI to the terminal

We sent this note to our customers to let them know that Braintrust has raised a new round of funding, and thank them for their support. While the money is exciting, our focus hasn't changed: we're building Braintrust to help our customers ship quality AI products. In 2026, AI is moving to production but teams have never had less conviction about what will fail next. Our customers are building AI products that serve millions and simply need to work. If Braintrust makes their lives easier and their products better, I know we are doing our job. Thank you to @ICONIQCapital for leading our Series B, and to @a16z, @GreylockVC, @basecasevc, and @eladgil for doubling down. Thank you to the Braintrust team for all the incredible work you've done over the past year. And thank you to our customers, who have made this growth possible.

Lucky to be part of Braintrust before B, and after B the good is only going to get better. Happy to be part of the 🚀

@yagp you've left the music on the livestream during the awards livestream in San Francisco 2026.

new kanban view for working through review tasks we're quite excited about how teams are treating annotation like real tasks that should be prioritized and solved. it's our job to make that easy and fun!

Code search in 2026 vs in the past. Would love to see a score/eval of my generated search, though, to see if the AI missed an instantiation.

We've eliminated user-based pricing. Invite more engineers, PMs, and cross-functional partners and build quality AI together.

Trace lineup dropped → braintrust.dev/trace Speakers from @tryramp, @Replit, @Dropbox, @Zendesk, @NotionHQ, @mintlify, @modal & more! * Feb 25 * California Academy of Sciences [SF] * Space is limited. In-person only.

@github would love if the diff UI allowed me to toggle on/off the wrapping so I can read PR reviews on a small screen on the Caltrain

Excited to be part of @braintrust's first user conference. No gimmicks just pure real world AI engineering goodness from the best products and companies fully invested in a better user experience with AI.

We stop debating *how* something is done and start scrutinizing *what* it should do. We become designers of intent.

This isn't about writing less code. It's about focusing on the right code. The contracts. The boundaries. The intent.

A mental model for the future of dev work 🧵

You're absolutely right... 🤖 🤛

With enough tokens, all bugs are shallow.

I wonder what the future Github insights should show. % of commits by ai, % of lines by ai, and so on? Seems like that gamification is no longer as appealing in today's world. Perhaps a new # of shipped features or value added that is inferred may be more appropriate.

Context switching hurts. If we can figure out a way in this AI world to improve our context switching. Would be profitable and sustainable

We're hosting the official @vercel Ship AI afterparty with our friends at Browserbase. Come hang out with other builders in SF on Oct 23: luma.com/gxgoscgt