The Agent2Agent protocol and how AI agents from different teams and vendors work together.
What it means for one agent to delegate to another, and the problems that appear immediately.
How one agent finds out what another can do, and why descriptions are the hard part.
Who is acting, on whose behalf, with what authority — and who answers when it goes wrong.
20 in this topic
An introduction to A2A, the open protocol that lets AI agents built by different teams and vendors work together.
A2A 1 min read 9 Aug 2025 For people
How the Agent2Agent protocol and the Model Context Protocol differ, and why many systems use both.
A2A 1 min read 8 Aug 2025 For people
How agents advertise their skills with Agent Cards, and how clients find and choose agents to work with.
A2A 1 min read 7 Aug 2025 For people
How work is tracked in A2A: task states, long-running work, requests for input and cancellation.
A2A 1 min read 6 Aug 2025 For people
The data that flows between agents in A2A: messages with text, file and data parts, and artifacts as outputs.
A2A 1 min read 5 Aug 2025 For people
How A2A keeps clients informed during long tasks, using server-sent events and webhooks.
A2A 1 min read 4 Aug 2025 For people
How A2A agents authenticate each other, authorise tasks and protect against malicious agents and content.
A2A 1 min read 3 Aug 2025 For people
The steps to expose an agent over the A2A protocol: define skills, publish a card, handle tasks and test.
A2A 1 min read 2 Aug 2025 For people
Patterns for combining agents over A2A: orchestrators, specialists, peer collaboration and marketplaces.
A2A 1 min read 1 Aug 2025 For people
Where agent-to-agent communication makes sense today: enterprise workflows, customer service, procurement and more.
A2A 1 min read 31 Jul 2025 For people
How A2A lets agents built with different frameworks and vendors work together, and what interoperability still requires.
A2A 1 min read 30 Jul 2025 For people
Keeping people in control when agents delegate to other agents: approvals, visibility and accountability.
A2A 1 min read 29 Jul 2025 For people
How to build dependable agent-to-agent integrations: failures, timeouts, retries and idempotency.
A2A 1 min read 28 Jul 2025 For people
How the skills in an Agent Card determine whether client agents delegate the right work to your agent.
A2A 1 min read 27 Jul 2025 For people
Tracing requests as they pass between agents so multi-agent systems can be debugged and audited.
A2A 1 min read 26 Jul 2025 For people
An overview of protocols for AI agents — MCP, A2A and others — and how they fit together.
A2A 1 min read 25 Jul 2025 For people
Adopting agent-to-agent communication in organisations: governance, catalogues, security and rollout.
A2A 1 min read 24 Jul 2025 For people
How to test that agents discover, delegate to and work with each other correctly before relying on them.
A2A 1 min read 23 Jul 2025 For people
Why A2A lets agents collaborate without sharing their reasoning, tools or memory, and what that means for trust.
A2A 1 min read 22 Jul 2025 For people
Open questions and likely developments as agents from different organisations increasingly work together.
A2A 1 min read 21 Jul 2025 For people