A2A Protocol (Agent-to-Agent)
A communication standard that enables AI agents built on different frameworks and by different vendors to discover, authenticate, and collaborate with each other. A2A protocol aims to create interoperability across the agent ecosystem.
The Agent-to-Agent protocol addresses the fragmentation problem in the agent ecosystem. As organizations deploy agents built on different frameworks (LangChain, CrewAI, custom solutions), these agents need standardized ways to communicate, share context, and coordinate tasks. A2A provides this interoperability layer, similar to how HTTP standardized web communication.
For engineering teams building agent infrastructure, A2A is important to track even if adoption is still early. The protocol covers agent discovery (finding what agents are available and what they can do), capability negotiation (determining if an agent can handle a specific task), task delegation (handing off work with appropriate context), and result reporting (returning outcomes in a standard format). Google introduced A2A as a complement to MCP, with MCP handling agent-to-tool communication and A2A handling agent-to-agent communication. As your agent ecosystem grows, interoperability standards will determine how easily you can integrate third-party agents and expose your agents to partners.
Related Terms
Model Context Protocol (MCP)
An open standard that defines how AI models connect to external tools, data sources, and services through a unified interface. MCP enables agents to dynamically discover and invoke capabilities without hardcoded integrations.
Tool Use
The ability of an AI model to invoke external functions, APIs, or services during a conversation to perform actions beyond text generation. Tool use transforms language models from passive responders into active problem solvers.
Function Calling
A model capability where the AI generates structured JSON arguments for predefined functions rather than free-form text. Function calling provides a reliable bridge between natural language understanding and programmatic execution.
Agentic Workflow
A multi-step process where an AI agent autonomously plans, executes, and iterates on tasks using tools, reasoning, and feedback loops. Agentic workflows go beyond single-turn interactions to accomplish complex goals.
ReAct Pattern
An agent architecture that interleaves Reasoning and Acting steps, where the model thinks about what to do next, takes an action, observes the result, and repeats. ReAct combines chain-of-thought reasoning with tool use in a unified loop.
Chain of Thought
A prompting technique that instructs the model to break down complex problems into sequential reasoning steps before producing a final answer. Chain of thought significantly improves accuracy on math, logic, and multi-step tasks.