How Figma Uses AI Agents for Security
Not a pilot. Figma deployed AI agents across its security operations—resolving complex alerts 70% faster.
Why it matters
A real deployment case study showing how agents handle multi-step investigative work (alert triage, incident search, system checks, remediation) with measurable productivity gains. Practitioners building or deploying agent systems get a concrete blueprint; enthusiasts see agent adoption moving into enterprise security ops.
The key facts
9 to knowFigma built AI agents for security alert investigation, incident search, system checks, and code-fix generation
Agents learn from previous investigations to reduce repetitive work
70% faster resolution of complex alerts
Multi-step autonomous workflow: alert investigation → past incident search → system checks → code fixes
Real production deployment (not a research project or pilot mentioned as such)
Figma built agents to investigate security alerts, search incidents, check systems, prepare code fixes
70% faster resolution of complex security alerts
Engineering team documented the build process and deployment
Real production use case, not a pilot or demo
Go to the source
InfoQ AI/MLinfoq.com
Publisher excerpt: The engineering team at software company Figma recently documented how they built AI agents to help their security team investigate alerts, search past incidents, check company systems, and even prepare code fixes. The agents learn from previous investigations, reducing repetitive work and helping…