Agent Fix: New Agentic Workflow & Claude Model Upgrade
Snyk upgraded Agent Fix to use Claude models with enhanced agentic workflows, including agentic retries that detect and correct deviations from security best practices, dynamic few-shot prompting for secure examples, and full language coverage across all Snyk Code languages. Performance improved significantly with Sonnet and Opus models showing 10+ percentage point gains on Snyk's Golden Test benchmark.
New Model & New Architecture
We're happy to announce we're upgrading Agent Fix to use the Claude family of models enhanced by Snyk's tooling and intelligence. This move delivers the following major improvements:
Security & Functional Enhancements
Agentic Retries: Our new workflow now detects where code suggestions deviate from security best practices. Instead of discarding the result, the system analyzes the failure and injects tailored guidance into the agent's subsequent attempts.
Dynamic Few-Shot Prompting: We now use the same training set used to fine-tune our internal model to dynamically provide secure fix examples for the new model to follow.
Expanded Support
Full Language Coverage: We will enable support for all Snyk Code languages on Day 1, removing previous limitations on language availability.
Comprehensive Rule Support: AI-powered fixes are now available for all supported rules and vulnerability types across the platform.
Measurable Impact
Golden Test Benchmark: Both Sonnet 4.6 and Opus 4.6 saw improved performance against Snyk’s Golden Test benchmark (72.4% to 82.5% and 74.6% to 85.4% respectively) with this new architecture vs. the models on their own.
Check out the blog for more details. This update started rolling out on May 26th and will reach 100% by end of day on May 28th.
Source: original entry ↗
More from Snyk
Follow Snyk to get its new changes in your feed and email digest.
Snyk CLI v1.1308.1 released
HTML report output is now available by default without preview features, and project names are consistently displayed in test summaries. This release also patches multiple security vulnerabilities.
Pending ignore requests now visible on Project's Issues page
Issues with pending ignore requests now display a clear "Pending Ignore Request" status on the Issues page and in issue details, with filtering support. The issues API now reports pending as part of an issue's ignore status for programmatic distinction of open, pending, and ignored findings.
Snyk Code October update: improved analysis and more findings
Snyk Code now analyzes projects more deeply and accurately across Java, Kotlin, Go, TypeScript, JavaScript, Python, C#, PHP and Ruby, with significantly more findings reported. Improvements include better import resolution via config files, corrected PHP typing, expanded library coverage, new vulnerability detection rules, and enhanced template and serverless application analysis.