Promptfoo
The AI Security Platform that catches vulnerabilities in development
Promptfoo is an AI security testing platform that helps developers and security teams find and fix vulnerabilities in AI applications, agents, and RAG systems before they ship. It automates red teaming by generating context-aware attacks such as prompt injections, jailbreaks, and PII leaks tailored to the specific application. The platform integrates into CI/CD pipelines and developer workflows, providing remediation guidance directly in pull requests.
Promptfoo connects to AI apps and workflows, generates thousands of context-aware adversarial attacks using real-time threat intelligence, and surfaces security findings with remediation steps directly in developer pull requests.
enterprise security directors and developers building AI applications
Background.
- Status
- launched
- Business model
- freemium
Similar projects.
Editorial take on the space this project sits in — momentum signals, adjacent moves, our call on whether the wedge is real. Get pinged when we publish a new read or when the landscape shifts.
Have a take on this space?
Tell us what you’d build differently, where you think the incumbents miss, or what we’ve gotten wrong about this project. Comments + reactions are coming soon.