Skip to content

Standard

Agent2Agent

Agent2Agent (A2A) is an open protocol, originally developed by Google, that lets AI agents built on different frameworks communicate and work together.

Known aliases

  • A2A

Current stories

investConfirmed3 publishers

TRM sizes this year's AI agent payments on x402 at $4 million at the outside

BlackRock's new paper argues stablecoins are the rail built for sub-cent machine payments, and TRM Labs, examining $52.7 million of Coinbase x402 settlements, could attribute between 0.6% and 7.5% of the value to AI agents.

Perspective Coverage

3 publishers
Builder
Builder 29%
Operator
Operator 23%
Investor
Investor 48%

Reality

Evidence55
Adoption12
Hype gap+40
Incentives60
Confidence55
leadershipOne report1 publisher

A five-question test moves the sovereignty argument onto the permissions layer

A Forbes Tech Council column argues that an institution's control over what its agents may do decides sovereignty, and the European rules it cites were written for cloud vendors.

Publishers:forbes.com

Reality

Evidence45
Adoption
Not scored
Hype gap+22
Incentives45
Confidence50
productOne report1 publisher

Salesforce pipes live CRM actions into Amazon Quick and Gemini Enterprise over MCP

At Dreamforce 2026 the company said Model Context Protocol will carry its context and actions into both hyperscalers' agent products, while AWS agents move into Slack. The connector work becomes a scoping job.

Publishers:siliconangle.com

Reality

Evidence32
Adoption18
Hype gap+22
Incentives76
Confidence45
buildOne report1 publisher

Curator approval gates every record AWS Agent Registry shows a consumer

AWS now ships a first-party catalog for agents, tools, skills and MCP servers, moving the hard part off building them and onto whoever keeps the records current and clears the approval queue, a staffing question as much as a platform one.

Publishers:aws.amazon.com

Reality

Evidence46
Adoption28
Hype gap+24
Incentives88
Confidence57
buildOne report1 publisher

Six specifications decide whether an agent can move off the harness it was built on

Lock-in migrated from the model to the runtime that holds your tool grants, approval rules and learned state. Six specifications aim to make that runtime's contents portable, and half of them are one person's drafts.

Publishers:dev.to

Reality

Evidence36
Adoption24
Hype gap+27
Incentives74
Confidence42