# Braintrust's Ankur Goyal: Code review doesn't cover prompts

DevFeed: [Braintrust's Ankur Goyal: Code review doesn't cover prompts](<https://devfeed.tech/articles/braintrust-s-ankur-goyal-code-review-doesn-t-cover-prompts-1948.md>)

Original publisher: [Read original article](<https://1password.com/blog/prompt-changes-security-review>)

Author: info@1password.com (Chris Fowler)

Published: 2026-06-30T00:00:00Z

Content type: article

Language: en

Sources: [Blog on 1Password Blog](<https://devfeed.tech/sources/blog-on-1password-blog.md>)

Topics: [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [AI, ML & Data Engineering](<https://devfeed.tech/topics/ai-ml-data-engineering.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [developers](<https://devfeed.tech/tags/developers.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [podcasts](<https://devfeed.tech/tags/podcasts.md>), [review](<https://devfeed.tech/tags/review.md>), [security](<https://devfeed.tech/tags/security.md>)

## AI overview

A Zero-Shot Learning episode examines AI observability and the security risk of treating prompt changes differently from code changes. It argues that prompts can alter agent behavior, data exposure, tool use, and credential access without passing standard review controls.

## Source excerpt

Zero-Shot Learning is a podcast about how AI gets built, secured, and deployed. Hosted by Nancy Wang, 1Password CTO, and Dev Tagare, Senior Director of Engineering at Google, it's a builder's view of the architecture and the decisions it takes to ship with AI. Ankur Goyal, Founder and CEO of Braintrust, which bills itself as "the AI observability platform," joined Zero-Shot Learning to talk about the problem every team shipping AI eventually faces, you can build something that works and then watch it quietly become something that doesn't. Braintrust sits in the iteration loop for AI products, helping teams trace production events, turn behavior into eval datasets, compare prompt or model changes, and catch regressions before they reach users. For teams building agents, quality depends on whether the system's behavior remains useful and safe as prompts, models, tools, and user inputs change. In this episode, what begins as a conversation about evaluation frameworks and production feedback loops reveals a security gap many teams may leave open: prompt changes are behavior-shaping production artifacts. They can change what agents do, what data they surface, which tools they call, and how they use access and credentials. Why don't prompt changes go through the same security review as code? "I think enterprise developers are more comfortable iterating quickly on prompts than they are changing the underlying code," Nancy said. Before code is sent to production, a developer commits to version control, opens a pull request, waits for peer review, passes automated security scans, and gets sign-off before anything merges. The process documents who changed what, when, and why. By contrast, prompt changes often live outside the codebase, stored in a database row, prompt-management tool, or platform dashboard that a product manager or operations team can update directly. There are often no pull requests for review, no security scans, and sometimes even no recorded change a secur