4 posts tagged with "agentic-ai"

Agent A asks Agent B to do a task. Agent B needs something from Agent A, so it asks. Agent A, to answer, asks Agent B again. How do you stop that recursion?

Carry a signed delegation chain with the call: a record of which agents it has already passed through. Check it before calling the next agent. With strict agent matching and enforcement turned on, a return to an agent already in the chain stops there. In the DVARA AI governance platform, you can also allow a return for a different skill. The choice matters, as does requiring agents to pass the chain along: a signature prevents edits, but it cannot stop an agent from leaving the chain out.

For two years the story of enterprise AI has been an agent calling a model, and — more recently — an agent calling a tool. There's a third call now, and most teams can't see it: an agent calling another agent. That hop has a name — agent-to-agent (A2A) — and it is the least-governed surface in the entire AI stack.

This post is a practical definition of A2A: what the protocol actually is, why the delegation hop between two agents is a blind spot your existing controls don't cover, and what it takes to govern it.

An agent can keep sensitive data out of a model prompt and still leak it in the next tool call. MCP arguments and responses are separate data paths, so they need their own policy, PII handling, and audit controls.

An AI agent can call a tool, read the result, and decide what to do next. That makes it useful. It also means one bad decision can repeat at machine speed: another database query, another email, another refund attempt, another billable model call.