--- title: Beyond regex: Harvesting security logic with LLMs description: Red Hat's SastAI initiative, developed in collaboration with NVIDIA and IBM Research, automates false positive identification in static application security... canonical: https://daily.dev/posts/beyond-regex-harvesting-security-logic-with-llms-prba6xlja twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Beyond regex: Harvesting security logic with LLMs | daily.dev og:description: Red Hat's SastAI initiative, developed in collaboration with NVIDIA and IBM Research, automates false positive identification in static application security... og:url: https://daily.dev/posts/beyond-regex-harvesting-security-logic-with-llms-prba6xlja og:image: https://api.daily.dev/og/posts/pRBa6xlja.png og:image:alt: Beyond regex: Harvesting security logic with LLMs 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. # Beyond regex: Harvesting security logic with LLMs **[Red Hat Developer](https://daily.dev/sources/rhdev)** · 6 min read · 0 upvotes · 0 comments ## Summary Red Hat's SastAI initiative, developed in collaboration with NVIDIA and IBM Research, automates false positive identification in static application security testing (SAST) using generative AI. The system employs a multi-stage agentic workflow combining RAG, semantic code search, and a novel pattern harvesting mechanism. Pattern harvesting extracts recurring security logic from ~8,000 human-annotated findings using stratified k-fold cross-extraction, iterative refinement, and just-in-time (JIT) context injection to avoid context bloat. A two-tiered model strategy uses large frontier models for pattern extraction and mid-range (50–100B parameter) models for inference. The approach achieved approximately 10% uplift over the baseline SastAI model, with plans for continuous learning loops and potential open sourcing. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [How pairing SAST with AI dramatically reduces false positives in code security](https://daily.dev/posts/how-pairing-sast-with-ai-dramatically-reduces-false-positives-in-code-security-r208wlnco) · InfoWorld · 0 upvotes · 0 comments - [AI SAST: Code Security for the Agentic SDLC](https://daily.dev/posts/ai-sast-code-security-for-the-agentic-sdlc-sxvc4pirt) · SD Times · 0 upvotes · 0 comments - [Introducing our open source AI-native SAST](https://daily.dev/posts/introducing-our-open-source-ai-native-sast-ufkhzq6e7) · Datadog · 16 upvotes · 0 comments - [What happens when you add AI to SAST](https://daily.dev/posts/what-happens-when-you-add-ai-to-sast-2tcivc1ph) · InfoWorld · 0 upvotes · 0 comments - [What is AI SAST?](https://daily.dev/posts/what-is-ai-sast--ulp7q7jo3) · Aikido Security · 0 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#llm](https://daily.dev/tags/llm), [#rag](https://daily.dev/tags/rag), [#agentic-ai](https://daily.dev/tags/agentic-ai) [View this post on daily.dev](https://daily.dev/posts/beyond-regex-harvesting-security-logic-with-llms-prba6xlja) ```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":"Beyond regex: Harvesting security logic with LLMs","url":"https://daily.dev/posts/beyond-regex-harvesting-security-logic-with-llms-prba6xlja","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/beyond-regex-harvesting-security-logic-with-llms-prba6xlja"},"datePublished":"2026-06-24T07:36:28.923Z","dateModified":"2026-06-24T07:36:59.927Z","description":"Red Hat's SastAI initiative, developed in collaboration with NVIDIA and IBM Research, automates false positive identification in static application security...","image":"https://media.daily.dev/image/upload/s--CxzD6vbw--/f_auto/v1722860399/public/Placeholder%2005","thumbnailUrl":"https://media.daily.dev/image/upload/s--CxzD6vbw--/f_auto/v1722860399/public/Placeholder%2005","isAccessibleForFree":true,"articleSection":"Red Hat Developer","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":"Red Hat Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/2a8895f3216c4900bdc455585a4ad3e4","url":"https://daily.dev/sources/rhdev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/beyond-regex-harvesting-security-logic-with-llms-prba6xlja","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,llm,rag,agentic-ai","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Red Hat Developer","item":"https://daily.dev/sources/rhdev"},{"@type":"ListItem","position":3,"name":"Beyond regex: Harvesting security logic with LLMs"}]} ```