Auto Agent Protocol – open A2A profile lets AI agents talk to car dealerships
The Auto Agent Protocol (AAP) is an open A2A profile enabling AI agents to interact with car dealerships by discovering inventory, accessing dealership information, and submitting leads using standardized messages based on A2A v1.0. It supports two communication bindings—JSON-RPC 2.0 and HTTP+JSON—and includes mappings to the legacy ADF/XML format for compatibility with existing CRM systems. The current v0.1 release does not include support for authentication, payments, financing, or trade-in valuations.
- ▪Auto Agent Protocol (AAP) is built on the A2A v1.0 protocol and enables AI agents to communicate with automotive retailers using typed messages.
- ▪Compliant dealer agents must publish an agent-card.json with the AAP automotive extension URI and implement seven required automotive skills.
- ▪AAP supports both JSON-RPC 2.0 and HTTP+JSON bindings, with identical payloads for invoking skills.
- ▪The v0.1 version includes field-by-field mapping to ADF/XML to ensure compatibility with legacy dealer CRM systems.
- ▪AAP does not currently support authentication, payments, financing, RFQ/quote flows, trade-in valuations, or reservations in v0.1.
Opening excerpt (first ~120 words) tap to expand
Auto Agent Protocol (AAP) The A2A v1.0 Automotive Retail Profile. AAP is the open A2A profile that lets AI agents discover dealerships, browse inventory, and submit consented leads through typed automotive messages riding on top of A2A v1.0. A compliant dealer agent is an A2A agent that publishes an agent-card.json with the AAP automotive extension URI (https://autoagentprotocol.org/extensions/a2a-automotive-retail/v0.1) and implements the seven required automotive skills. Buyer agents can use either A2A binding — JSON-RPC 2.0 or HTTP+JSON — to invoke the same skills with identical payloads.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.