How we secure Figma’s internal systems with agents

What this post added

This post details the development of a new security alert triage system at Figma. It describes the implementation of a RAG layer using AWS Bedrock Knowledge Bases and Amazon Kendra to index and retrieve historical alert data and investigation context. It also outlines the addition of an agentic layer built with Tines, which routes requests to specialized agents with access to tools for Okta, endpoint security (Santa), and cloud security (Wiz) to automate alert investigation and response. The post highlights the technical details of indexing, querying, and agent tool integration, including code snippets for attribute definition, query building, and context addition.