---
title: "How to wire a remote agent into your workflow with A2A"
description: "A2A lets agents discover each other and hand off tasks over JSON-RPC 2.0. This guide walks through exposing an Agent Card, sending typed messages, connecting a remote service, and routing failures to a human review checkpoint."
---

# How to wire a remote agent into your workflow with A2A

**Type:** [How to](https://yomu.fyi/visual-explainers/category/how-to.md)

![Four-step horizontal diagram showing how to connect a remote agent with A2A: expose an Agent Card, send JSON-RPC messages, connect via RemoteA2aAgent, and route failures to manual review.](https://yomufyi.s3.us-east-1.amazonaws.com/visual-explainers/3bbc08d0-8775-41b1-b369-413684fc61c3/image-b1c9203b-6f89-4837-9f9b-28bd44fad96a.webp)

> A2A lets agents discover each other and hand off tasks over JSON-RPC 2.0. This guide walks through exposing an Agent Card, sending typed messages, connecting a remote service, and routing failures to a human review checkpoint.

## Explanation

Agent2Agent (A2A) is a protocol for letting autonomous agents discover each other and hand off work, rather than treating every agent as a stateless API call. A service announces itself with an Agent Card at /.well-known/agent.json, then exchanges JSON-RPC 2.0 messages with typed Message Parts and task states such as submitted, working, completed, and failed. To connect a remote agent, you expose its card, register it as a sub-agent in your orchestration layer, share pipeline state through a context object, and route failures to a manual review path. The payoff is language-independent, decoupled collaboration: a Python agent can call a Go service for deterministic checks, and you keep a clear audit trail for regulated work.

**Tags:** [A2A](https://yomu.fyi/topic/a2a.md), [Agent Development Kit](https://yomu.fyi/topic/agent-development-kit.md), [AI Agents](https://yomu.fyi/topic/ai-agents.md), [API](https://yomu.fyi/topic/api.md), [MCP](https://yomu.fyi/topic/mcp.md)

## Related reading

### [Anthropic acquires Stainless](https://yomu.fyi/post/anthropic-acquires-stainless.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Published: Sep 9, 2026
- Type: Announcement

Anthropic is acquiring Stainless, an SDK and MCP server tooling company founded in 2022, to expand how Claude and other agents connect to data and tools. Stainless has generated every official Anthropic SDK since the API’s early days and is used by hundreds of companies to produce SDKs, CLIs, and MCP servers from API specifications. Its tooling supports TypeScript, Python, Go, Java, and other languages, with libraries designed to feel native while remaining fast and reliable. The companies say combining their teams will advance developer experience and agent connectivity on the Claude Platform, while Stainless’s founder, Alex Rattray, said the team will continue its work within Anthropic.


### [Announcing ADK for Kotlin 1.0: Building Production-Ready AI Agents in Kotlin, Android, and Beyond](https://yomu.fyi/post/announcing-adk-for-kotlin-1-0-building-production-ready-ai-agents-in-k.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Guillaume Laforge
- Published: Sep 9, 2026
- Type: Announcement

ADK for Kotlin 1.0 is announced as a general availability release for building AI agents with Kotlin across Android, JVM server applications, and Java-integrated systems. The release targets a production-ready toolkit while preserving an idiomatic, lightweight, composable approach, and it reaches feature parity with ADK 1.0 Core, including hierarchical agents, context compaction, human-in-the-loop confirmation, resumable sessions, annotated tools, and Java interoperability. A Kotlin Multiplatform core stays agnostic to model backends, session providers, and memory systems, while Android extensions support LiteRT-LM, ML Kit (beta), Firebase AI Logic, Room, AppSearch, and file artifacts. The database incident example combines compile-time KSP-generated function schemas, suspend-capable @Tool functions, and dynamically loaded SKILL.md playbooks with progressive disclosure. The release provides 1.0.0 dependencies, documentation, a repository, and sample applications.


### [Build Cross-Language Multi-Agent Team with Google’s Agent Development Kit and A2A](https://yomu.fyi/post/build-cross-language-multi-agent-team-with-google-s-agent-development.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Shubham Saboo, Eric Dong
- Published: Jun 22, 2026
- Type: Tutorial

The post presents a contract-compliance pipeline in which a Python agent uses Gemini to extract contract terms and a Go service applies deterministic corporate-policy checks. It connects the services with the Agent2Agent (A2A) protocol and uses Google's Agent Development Kit (ADK), including RemoteA2aAgent, to expose the remote validator as a local sub-agent in a SequentialAgent. A2A supplies discovery through Agent Cards at /.well-known/agent.json, JSON-RPC 2.0 messaging through message/send, typed Message Parts, and task states such as submitted, working, completed, and failed. Pipeline state is shared through ADK's ToolContext.state, with failures transitioning to MANUAL\_REVIEW for human legal review when the Go service is unavailable. The accompanying open-source application demonstrates live handoffs, policy verdicts, and simulated network faults, while the conclusion emphasizes language independence, decoupling, resilience, and deterministic auditing.


### [How A2A is Building a World of Collaborative Agents](https://yomu.fyi/post/how-a2a-is-building-a-world-of-collaborative-agents.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Alan Blount, Frank Guan, Nick Losier
- Published: Jun 18, 2026
- Type: Announcement

A2A, launched one year before this June 18, 2026 update, is presented as a common language for conversational, dynamic agents that need to collaborate and hand off tasks securely rather than behave like stateless tools. The protocol uses black-box handoffs to keep sensitive data and proprietary processes encapsulated, prevent context pollution, support clarifying exchanges, and distribute specialized workloads across teams or services. Foldrun demonstrates this model by exposing protein-structure prediction as a standalone agentic interface that manages long-running tasks, adjusts parameters based on prediction confidence, and selects among AlphaFold 2, OpenFold 3, and Boltz-2 depending on the molecule. In an A2A-compliant environment, users can register Foldrun and delegate work in natural language without custom glue code, while a primary agent handles other research tasks. The post also cites applications in commerce, streaming, IT operations, and regulated telecom, while Python and Go SDKs are 1.0 GA.