Evaluations are essential for determining the quality, performance, and effectiveness of software during development. Methods like code reviews and automated testing are commonly used to detect bugs, ensure requirements compliance, and assess software reliability. However, evaluating LLMs is uniquely challenging due to their complexity, versatility, and potential for unpredictable behavior.
Ankur Goyal, CEO and Founder of Braintrust Data, offers an end-to-end platform for AI application development, focusing on making LLM development robust and iterative. Ankur founded Impira, later acquired by Figma, where he led the AI team. He discusses Braintrust and the challenges of developing evaluations in non-deterministic contexts.
Sean, with experience as an academic, startup founder, and Googler, has published works on various topics from AI to quantum computing. As an AI Entrepreneur in Residence at Confluent, he focuses on AI strategy and thought leadership. You can connect with Sean on LinkedIn.
[Transcript of the episode available here.](http://softwareengineeringdaily.com/wp-content/uploads/2025/05/SED1792-Braintrust.txt)
### Sponsors