Braintrust founder and CEO Ankur Goyal examines why AI learning happens after launch
In this episode
Before founding Braintrust, Ankur Goyal began as a builder, developing distributed systems and applied AI and machine learning products. Like many developers, he faced a persistent problem: How do you know if what you’re shipping will actually work in production? In this episode, Ankur talks to 1Password CTO Nancy Wang and Google Gemini’s Dev Tagare about why AI development needs feedback loops and how evals help teams move faster.
How to close the gap between ship and prod
Evals are becoming the new product development loop
Feedback loops help teams learn from unpredictable AI behavior in production
Traditional tracing tools don’t explain AI failures
Choosing an LLM is more like choosing a database than a CPU
The agent layer should be treated as disposable
Also available in audio format on the following platforms: Apple Podcasts, Spotify
Ankur Goyal
Ankur Goyal is the founder and CEO of Braintrust, the AI observability platform that connects evals and observability in one workflow. Prior to founding Braintrust, Ankur founded Impira, a platform for extracting unstructured data from documents, which was acquired by Figma. He was also VP of Engineering at MemSQL, worked at Microsoft, and studied computer science at Carnegie Mellon.
Get the episode transcript
More episodes
OpenAI Agent Security Lead Fotis Chantzis discusses one of the biggest unsolved problems in AI
Vercel Chief Product Officer Tom Occhino reflects on React and how AI transforms software creation
