Core Objects

Use these references to describe an agent, exchange messages, track tasks, and return results. Each object reference explains its fields and protocol rules, with examples from the official documentation. For an overview of how the objects relate, read A2A Key Concepts and Components .

ObjectWhat it isRead this page when
Agent CardThe JSON document an agent publishes to describe itselfYou publish an agent, or need to discover and select one
TaskA stateful unit of work with a lifecycleYou handle long-running work, multi-turn input, or cancellation
MessageOne turn of communication between client and agentYou send requests or return clarifying and status messages
PartThe content container: text, file, or structured dataYou exchange files or JSON, not only text
ArtifactA concrete output produced by a taskYou return results, or stream them in chunks

When declaring agent capabilities and authentication, consult these Agent Card objects:

ObjectWhat it isRead this page when
AgentSkillOne entry in the card’s skills listYou describe what your agent can do, or read another agent’s card
SecuritySchemeHow a card declares authentication, from API keys to OAuth 2.0You protect an agent endpoint, or need to know how to authenticate to one

How the objects fit together

A client reads the Agent Card to learn how to reach an agent and what it can do. It then sends a Message, whose content is one or more Parts. The agent answers with either a direct Message or a Task. A Task moves through states, and the results it produces are Artifacts, which are also made of Parts.

Related pages

Source: A2A official documentation: Key Concepts and Protocol Data Model