Building a Multi-Agent Security Pipeline with Google's A2A Protocol and GitGuardian

Andy Rea, our CTO, recently published a comprehensive guide on the GitGuardian blog demonstrating how to build a multi-agent security pipeline using Google's Agent-to-Agent (A2A) protocol.

What the demo shows

The demo showcases how to wire up multiple AI agents using Google's Agent Development Kit (ADK) and the A2A protocol. The pipeline integrates GitGuardian to scan content for secrets, demonstrating a practical application of multi-agent orchestration for security automation.

Key technologies

• Google Agent Development Kit (ADK) — Google's framework for building and deploying AI agents
• A2A Protocol — Google's Agent-to-Agent protocol for inter-agent communication
• GitGuardian — Secrets detection and security scanning

Why this matters

As AI agents become more prevalent in development workflows, the ability to orchestrate multiple specialised agents becomes critical. This demo provides a practical blueprint for building security-focused agent pipelines that can automatically detect and prevent secrets from being exposed in code and content.