Claire Vo · 3 min read · Product Teams
How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal
Read the original on lennysnewsletter.com →
Ankur Goyal explains how Braintrust uses AI agents, evals, and continuous integration to ship better software at scale. The discussion covers delegating complex architecture work to agents, turning evals into a PRD-like guide for AI, and encoding designer taste into scoring to scale quality with CI/CD as a lever for engineering velocity.
Key Takeaways
- AI agents can tackle complex architecture and infrastructure tasks at scale, beyond what a single engineer can do.
- Evals provide a repeatable, concrete way to define 'what good looks like' and can function as a modern PRD for AI systems.
- The agent line framework helps teams decide which decisions to delegate to agents and how to manage concurrent workflows.
- Encoding designer taste into scoring functions enables quality to scale beyond one person's influence.
- Investing in CI/CD and rigorous benchmarking is a high-leverage approach to speed up AI-accelerated engineering velocity.
Excerpt
In this episode, I sit down with Ankur Goyal , founder and CEO of Braintrust, the AI evals and observability platform used by teams like Notion, Stripe, Vercel, and Zapier. This one is for the senior engineers, staff engineers, VPs of engineering, and CTOs in my audience. We get into how coding agents can take on deeply technical architecture and infrastructure work that no single human engineer could tackle before, and then we demystify evals so you can use them to make your AI products better without touching the implementation. Listen or watch on YouTube , Spotify , or Apple…