Zero-Shot Learning

Stop guessing if your AI works | Ankur Goyal from Braintrust

Episode Summary

Your code review covers code. It doesn't cover prompts. 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.

Episode Notes

In this episode:

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

 

Zero-Shot Learning is a builder-to-builder podcast about how AI systems are designed, deployed, and secured. Subscribe for more.

 

Go deeper:

Episode companion blog: https://www.1password.com/blog/prompt-changes-security-review

1Password Developer newsletter: https://1password.com/developer-newsletter

 

Ankur:

LinkedIn: https://www.linkedin.com/in/ankrgyl/

 

Connect with 1Password

1Password.com

1Password Developer newsletter: https://1password.com/developer-newsletter

Build securely with 1Password Developer: https://developer.1password.com/