Datadog has open sourced an AI-native Static Application Security Testing (SAST) tool that uses LLMs to detect code vulnerabilities with greater accuracy than traditional rule-based approaches. The tool works in four steps: heuristic-based file identification, context retrieval, LLM-based analysis, and post-processing with

6m read timeFrom datadoghq.com
Post cover image
Table of contents
What is AI-native SAST?How does Datadog’s AI-native SAST feature work?Fine-tuned performanceEvaluating accuracy against the OWASP BenchmarkWhy open source it?The future of AI-enhanced SAST at Datadog

Sort: