Evals are the new PRD. Here is the playbook with the CEO of the leader in the space (Ankur Goyal, Founder and CEO, Braintrust)

About this episode

The episode discusses the importance of evals in product management and features a live demonstration with Ankur Goyal, CEO of Braintrust.

Today’s episode Most PMs treat evals like a quality gate. Something you run right before shipping, just to check the box. That is backwards . The best AI product teams treat evals as the starting point . They write the eval before the prompt. They iterate on the scoring function before the model. They use failing evals as a roadmap. That shift is what today’s episode is about. I sat down with Ankur Goyal, Founder and CEO of Braintrust. It is the eval platform used by Replit, Vercel, Airtable, Ramp, Zapier, and Notion. Braintrust just announced its Series B at an $800 million valuation . Users are running 10x more evals than this time last year. People log more data per day now than they did in the entire first year the product existed. In this episode, we build an eval entirely from scratch . Live. No pre-written prompts, no pre-written data. We connect to Linear’s MCP server, generate test data, write a scoring function, and iterate until the score goes from 0 to 0.75. Plus, we cover the complete eval playbook for PMs : If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab…

People in this episode

Host: Aakash Gupta

Guest: Ankur Goyal

Topics covered

• evals
• AI product teams
• scoring function
• product management
• iterative development

Keywords

• evals
• AI
• product management
• scoring function
• Braintrust
• Ankur Goyal
• iterative development

Sponsors

Kameleoon, Testkube, Pendo

Mentioned in this episode

Organizations: Braintrust, Replit, Vercel, Airtable, Ramp, Zapier, Notion

More episodes of The Growth Podcast

• How a VP of Product Uses Claude Without Producing Slop | Matthew Wensing, Customer.io · June 9, 2026 · 50 min
• How to Use Codex Like an OpenAI PM | Abhi Muchhal, PM OpenAI (ex-Meta and Nubank) · June 3, 2026 · 1h 7m
• How PMs Ship 100K Lines of Code at OpenAI with Ryan Lopopolo, Member of Technical Staff · May 25, 2026 · 1h 15m
• How to Run Evals in Claude Code with Aparna Dhinakaran, Founder and CPO of Arize · May 22, 2026 · 1h 20m
• Claude Code for Non-Technical PMs, with Andre Albuquerque · May 18, 2026 · 1h 10m
• PM's Guide to Claude - When to use Chat vs Cowork vs Code, with Pawel Huryn · May 14, 2026 · 1h 33m