# Evals, Feedback Loops, and the Engineering That Makes AI Work

Page: https://stenobird.com/podcast/ai-a16z-6874937/evals-feedback-loops-and-the-engineering-that-makes-ai-work
Text version: https://stenobird.com/podcast/ai-a16z-6874937/evals-feedback-loops-and-the-engineering-that-makes-ai-work.md
Podcast: [AI + a16z](https://stenobird.com/podcast/ai-a16z-6874937)
Published: 2026-02-17T17:15:00+00:00
Episode link: https://ai-a16z.simplecast.com/episodes/evals-feedback-loops-and-the-engineering-that-makes-ai-work-cqU91fWY
Audio file: https://mgln.ai/e/1344/afp-848985-injected.calisto.simplecastaudio.com/112866f3-1a50-4a8d-b12e-850b73e71b33/episodes/0a4f8869-211c-4465-91aa-860173e18e94/audio/128/default.mp3?aid=rss_feed&awCollectionId=112866f3-1a50-4a8d-b12e-850b73e71b33&awEpisodeId=0a4f8869-211c-4465-91aa-860173e18e94&feed=Hb_IuXOo
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/ai-a16z-6874937/episodes/evals-feedback-loops-and-the-engineering-that-makes-ai-work
Duration seconds: 2629

## Resource

Martin Casado speaks with Ankur Goyal, founder and CEO of Braintrust, about where engineering actually matters in AI and where it doesn't. They cover the open source vs closed source model cycle, why Chinese models are gaining ground faster than spending suggests, whether AI demand will eventually saturate, and the Bash vs SQL benchmark that challenges the "just give it a computer" approach to agents.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/ai-a16z-6874937/episodes/evals-feedback-loops-and-the-engineering-that-makes-ai-work/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/ai-a16z-6874937/evals-feedback-loops-and-the-engineering-that-makes-ai-work.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.