--- title: How Figma stays ahead of vulnerabilities with agents description: Figma's security team describes how they built an agentic security system that guards code at three stages: generation, pull request review, and historical... canonical: https://daily.dev/posts/how-figma-stays-ahead-of-vulnerabilities-with-agents-uui6x4kvc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: How Figma stays ahead of vulnerabilities with agents | daily.dev og:description: Figma's security team describes how they built an agentic security system that guards code at three stages: generation, pull request review, and historical... og:url: https://daily.dev/posts/how-figma-stays-ahead-of-vulnerabilities-with-agents-uui6x4kvc og:image: https://api.daily.dev/og/posts/uuI6X4kVc.png og:image:alt: How Figma stays ahead of vulnerabilities with agents og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # How Figma stays ahead of vulnerabilities with agents **[Figma](https://daily.dev/sources/figma)** · 20 min read · 0 upvotes · 0 comments ## Summary Figma's security team describes how they built an agentic security system that guards code at three stages: generation, pull request review, and historical auditing. The system uses Claude Code (Opus 4.8) and Codex (GPT-5.6) to review every PR at ~$0.50 median cost, with a 70%+ precision target before enabling developer-facing comments. A key insight is that precision must be improved before recall, and that precision and recall require different measurement approaches — precision from live PR author feedback, recall from replaying against known-bad commits. The team built a 99-line, 2,560-word policy of 68 precedents that doubles as a threat model, shared across all three agent stages. Self-improvement loops automatically update the policy when new bugs are found or false positives are reported. An adjudicator pass raised recall by ~30%. Repo-wide auditing found 100+ latent vulnerabilities including two criticals missed by SAST. Agent hooks during code generation steer toward secure patterns just-in-time, reducing certain bug classes by ~50%. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How Figma Uses AI Agents for Security](https://daily.dev/posts/how-figma-uses-ai-agents-for-security-jbtkyohsy) · InfoQ · 1 upvotes · 0 comments - [How we secure Figma’s internal systems with agents](https://daily.dev/posts/how-we-secure-figma-s-internal-systems-with-agents-0csav3m0f) · Figma · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude-code](https://daily.dev/tags/claude-code) [View this post on daily.dev](https://daily.dev/posts/how-figma-stays-ahead-of-vulnerabilities-with-agents-uui6x4kvc) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"How Figma stays ahead of vulnerabilities with agents","url":"https://daily.dev/posts/how-figma-stays-ahead-of-vulnerabilities-with-agents-uui6x4kvc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/how-figma-stays-ahead-of-vulnerabilities-with-agents-uui6x4kvc"},"datePublished":"2026-07-23T22:06:44.307Z","dateModified":"2026-07-24T01:04:56.416Z","description":"Figma's security team describes how they built an agentic security system that guards code at three stages: generation, pull request review, and historical...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f8b650b847a31dfebbe474921b22482?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f8b650b847a31dfebbe474921b22482?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Figma","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Figma","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/d81fd85ddaea4d25a658694de448118f","url":"https://daily.dev/sources/figma"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/how-figma-stays-ahead-of-vulnerabilities-with-agents-uui6x4kvc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,claude-code","timeRequired":"PT20M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Figma","item":"https://daily.dev/sources/figma"},{"@type":"ListItem","position":3,"name":"How Figma stays ahead of vulnerabilities with agents"}]} ```