What is A2A?
Agent2Agent protocol, a standard for how one AI agent hands a task to another agent clearly enough that the second one can trust it and act on it.
2 min read
A general-purpose assistant often doesn't finish a job itself, it delegates part of it, "book this exact room, these dates," to a more specialised agent. A2A structures that handoff: what's being asked, on whose behalf, by which agent, so the receiving side has real grounds to act rather than trusting an anonymous instruction. It's not a payment protocol and doesn't decide whether a task should be approved, just describes it precisely enough to be trusted.
Good for
Structuring a handoff between two agents so the receiving one can trust it.
Not good for
Deciding whether the handed-off task should be approved or paid for.
What is an agent credential?
A short-lived, scoped proof that an AI agent is who it claims to be, checked before a business trusts a request enough to act on it.
What is MCP?
Model Context Protocol, an open standard that lets an AI agent call into a business's own systems, checking live data or triggering a defined action, the way it would check availability or pull a menu.
What is UCP?
Universal Commerce Protocol, the checkout protocol that completes a purchase once an AI agent has already been connected, identified and authorised, handing a business back a confirmed order instead of an unverified promise.