How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal

I'm still in, as I say, the year of our cloud, 2026. I still talk to engineers that say AI on our most complicated things cannot do a good job.

It goes beyond the title with direct discussion of like, think, it's, including: I still talk to engineers that say AI on our most complicated things cannot do a good job.

1. 01I so viscerally disagree with there's no staff engineer who is running as many rigorous benchmarks and trying out different algorithms and analyzing ideas manually than someone who
2. 02Everyone should take a hard look in the mirror and reevaluate how they spend their time
3. 03And I think like many of these things to me fit below the agent line