miscsubjectsAI governance
A2A, from its own documents
Evidence review · model_contribution

A2A, from its own documents

· 2 min read
bundle · json · system map · manifest

Every copy includes §SELF — what this is, proof chain, and links to every other feature. No context required.

§SELF — this page explains the system
## §SELF — miscsubjects portable reference

**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.

**This widget:** `human_page` — **Human article page**
Rendered article with claims, sources, copy widgets, ask prompts.
- **article slug:** `what-is-a2a`
- **contains:** rendered article, copy widgets, claims, sources, ask prompts
- **how to use:** Use Copy for LLM or Copy system map — both paste without context.
- **read:** https://miscsubjects.com/a/what-is-a2a

### Logical proof (verify each step)
1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution
2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/what-is-a2a/sources
3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol
4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow
5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex
6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map

### Related features (explains other parts of the system)
- **bundle** — Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution. · https://miscsubjects.com/api/articles/what-is-a2a/bundle?format=markdown
- **ask** — Answer only from topology; creates question_node with gaps and ingest_hint. · https://miscsubjects.com/api/articles/what-is-a2a/prompts
- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/what-is-a2a/topology

### Full index
- JSON: https://miscsubjects.com/api/articles/system-map
- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown

*Not medical advice. Tier-honest. Cite claim/source ids.*

Agent2Agent is the protocol for the layer above tools: agents talking to other agents. Its repository states the problem it exists to solve — enabling "gen AI agents built on diverse frameworks by different companies running on separate servers to communicate and collaborate effectively — as agents, not just as tools." Google contributed it, the Linux Foundation governs it, and one year in it counts more than 150 supporting organizations. This page is the reference record, from the protocol's own repository and its foundation's announcements.

The one-line definition

The repo describes itself as "an open protocol enabling communication and interoperability between opaque agentic applications." The word doing the work is opaque. A2A's core design commitment is that agents cooperate without exposing internal state, memory, or tools — you interact with what an agent claims it can do, never with how it does it.

Mechanically it is deliberately boring: JSON-RPC 2.0 over HTTPS, with synchronous request/response, streaming over server-sent events, and asynchronous push notifications. Apache 2.0 licensed, 25,000 GitHub stars. Boring is the point; protocols win by being unobjectionable.

The agent card is the whole discovery model

An A2A agent publishes an agent card: a structured document describing its capabilities and connection details. Other agents read the card, decide whether this agent can do what they need, and open a session. The card is the unit of discovery, the same way a server entry is the unit of discovery in the MCP registry one layer down. Capability description moves to a machine-readable public record; negotiation happens against the record, not the implementation.

One year to 150 organizations

The Linux Foundation's April 9, 2026 announcement marked the protocol's first year: "more than 150 organizations supporting the standard," with production deployments on Google Cloud, Microsoft Azure (AI Foundry and Copilot Studio), and AWS (Bedrock AgentCore Runtime).

All three hyperscalers shipping the same agent-coordination protocol within a year is the notable fact. The last time cloud vendors agreed on anything that fast, it was Kubernetes.

The division of labor with MCP

The foundation states the boundary in one sentence: "A2A defines how agents communicate and coordinate with each other across organizational boundaries, while MCP defines how agents connect to internal tools and data sources." Tools below, agents above, one registry-shaped discovery mechanism at each layer.

What neither layer covers, and A2A's enterprise-readiness language only gestures at: how much authority travels with a delegated task. An agent card says what an agent can do; nothing in the protocol yet constrains what a particular caller may ask it to do beyond transport-level authentication. That open edge — delegation with enforceable limits — is where the current research literature points, and it is the axis on which agent-to-agent systems will differentiate next.

Evidence · 2 sources · swipe →chain 55a7b82ceb98 · verify chain · provenance
1 / 2

Key evidence

4 claims · tier-ranked · API
system
By April 9, 2026 A2A had 150+ supporting organizations and production deployments on all three hyperscalers.
sources: s2
system
A2A covers coordination across organizational boundaries while MCP covers tool connection; neither constrains how much authority travels with a delegated task beyond transport auth. First half documentary, second half analytical.
sources: s1, s2
systemlow confidence
A2A is an open Linux Foundation protocol (contributed by Google, Apache 2.0, 25k stars) enabling communication between opaque agentic applications over JSON-RPC 2.0/HTTPS.
sources: s1
systemlow confidence
Discovery works through agent cards: published structured descriptions of an agent's capabilities and connection details, read without exposing internals.
sources: s1
Model review6 contributions · 1 modelExpand the recursive review layer
1 / 6
claude-fable-5source_hunt
sources2026-07-24 16:11
1 source(s) added · 1 sources
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-is-a2a
it output
1 source(s) added
7efec30e7096bab6
claude-fable-5source_hunt
sources2026-07-24 16:11
1 source(s) added · 1 sources
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-is-a2a
it output
1 source(s) added
27b4f12086cbc401
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-is-a2a c4
it output
A2A covers coordination across organizational boundaries while MCP covers tool connection; neither constrains how much authority travels with a delegated task beyond transport auth. First half documentary, second half analytical.
a6f954fb1fab97b8
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-is-a2a c4
it output
A2A covers coordination across organizational boundaries while MCP covers tool connection; neither constrains how much authority travels with a delegated task beyond transport auth. First half documentary, second half analytical.
079c060e8a216211
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-is-a2a c4
it output
A2A covers coordination across organizational boundaries while MCP covers tool connection; neither constrains how much authority travels with a delegated task beyond transport auth. First half documentary, second half analytical.
70e75299fa3f08e5
claude-fable-5claim_post
claim2026-07-24 16:12
claim
inspect — what it was prompted & output
prompted with
(default writer prompt)

input: what-is-a2a c4
it output
A2A covers coordination across organizational boundaries while MCP covers tool connection; neither constrains how much authority travels with a delegated task beyond transport auth. First half documentary, second half analytical.
25c0aeab49c00365
Machine verification: /api/articles/what-is-a2a/contributions

Latest from the journal

Most recent pieces, site-wide

All articles →
The Disc Stackposted 2026-07-24the-disc-stackHerniated Discposted 2026-07-24herniated-discDegenerative Disc Diseaseposted 2026-07-24degenerative-disc-diseaseBPC-157 vs NSAIDs: Repair or Suppress?posted 2026-07-24bpc-157-vs-nsaidsAgentKit: a post-mortem in advanceposted 2026-07-24what-agentkit-was

Related articles

what-is-a2a · condition map

Open evidence map →
AgentKit: a post-mortem in advanceshared topicwhat-agentkit-wasMCP, from its own documentsshared topicwhat-is-mcpLangChain, from its own documentsshared topicwhat-is-langchainGRAIN: 2. What the Grain Favorsshared topicgrain-what-the-grain-favors
Ask this article · 6 suggested prompts
topology · JSON · question graph

Text the build (+14245134626) or WhatsApp — slug|question creates a question node. Paste evidence with ingest slug|q:NODE_ID|your paste.

What does the ledger say about this (system tier): "By April 9, 2026 A2A had 150+ supporting organizations and production deployments on all three hyperscalers."?
ask what-is-a2a claim c3 · paste includes §SELF
What does the ledger say about this (system tier): "A2A covers coordination across organizational boundaries while MCP covers tool connection; neither constrains how much authority travels wit…"?
ask what-is-a2a claim c4 · paste includes §SELF
What does the ledger say about this (system tier): "A2A is an open Linux Foundation protocol (contributed by Google, Apache 2.0, 25k stars) enabling communication between opaque agentic applic…"?
ask what-is-a2a claim c1 · paste includes §SELF
What does the ledger say about this (system tier): "Discovery works through agent cards: published structured descriptions of an agent's capabilities and connection details, read without expos…"?
ask what-is-a2a claim c2 · paste includes §SELF
What can you answer from your catalogue about A2A, from its own documents — and what remains open or unverified?
ask what-is-a2a gaps · paste includes §SELF
What are the strongest objections or counter-evidence on record against A2A, from its own documents?
ask what-is-a2a objections · paste includes §SELF
what-is-a2a · posted 2026-07-24 · updated 2026-07-24 · 6 prior revisions
Ledger API & provenance
Provenance · 7 model passes · tokens/cost unrecorded · 2 models
chain head 135899586fff26d8
voxel_batch_document_new cap:cap_e977bc9c49319139 · 2026-07-24 16:10 · tokens unrecorded · 2a1db0b66503
sources claude-fable-5 · 2026-07-24 16:11 · tokens unrecorded · d135d46097e2
sources claude-fable-5 · 2026-07-24 16:11 · tokens unrecorded · 7c7a20b3d01b
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 4c334f217d39
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · bf2b4b52cefc
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · fc88b4635ef1
claim claude-fable-5 · 2026-07-24 16:12 · tokens unrecorded · 135899586fff
verify chain →
Live ledger · 3 payloads · 1 turn
recent activity · inspect
X_POST dispatch · 2026-07-24 09:47 · t_ex4raawc
X_POST dispatch · 2026-07-24 09:47 · t_ex4raawc
X_POST mcp · HTTP 200 · 2026-07-24 09:47 · t_ex4raawc
view full ledger & cards →
REST + ledger
read GET /api/articles/what-is-a2a · GET /api/articles/what-is-a2a?format=post (the editable body)
create/replace POST /api/articles/what-is-a2a · PUT /api/articles/what-is-a2a (replace, keeps revision) · PATCH /api/articles/what-is-a2a (merge)
delete DELETE /api/articles/what-is-a2a
writes need header x-terminal-key
ledger provenance · sources · contributions · revisions · live ledger & cards
LLM bundle GET /api/articles/what-is-a2a/bundle?format=markdown — body + claims + sources + provenance + manifest
voxel graph GET /api/articles/what-is-a2a/voxels · constitution · ontology
post claim POST /api/protocol/claim · iMessage claim what-is-a2a|tier|assertion
system map GET /api/articles/system-map?format=markdown — root index; every widget self-explains via §SELF / _self
Add your experience or question
Think this article is wrong?
Call bullshit on CharlieOS →
Loading more articles…