GenAI PMA2A
A pattern for agent-to-agent communication and collaboration. The newsletter mentions it as part of a step-by-step approach to building multi-agent systems.
Key Highlights
- A2A is a pattern and protocol framing for how multiple AI agents communicate and collaborate.
- It became notable in the newsletter through Andrew Ng’s Agent2Agent Protocol course with Google Cloud and IBM Research.
- A2A was also cited as a practical building block for Python-based multi-agent systems alongside MCP.
- For AI PMs, A2A is most useful when defining agent handoffs, communication contracts, and reliability metrics in multi-agent products.
Overview
A2A, short for Agent-to-Agent (also referred to as the Agent2Agent Protocol), is a pattern for how multiple AI agents communicate, coordinate, and collaborate to complete work together. Instead of a single agent handling every task end-to-end, A2A enables a system design where specialized agents can pass messages, delegate subtasks, share context, and combine outputs. In the newsletter, A2A appears both as an emerging protocol-oriented concept and as a practical building block in step-by-step guides for creating multi-agent systems.For AI Product Managers, A2A matters because multi-agent products introduce new UX, reliability, and orchestration challenges beyond simple prompt-response applications. Once teams move from one assistant to several cooperating agents, they need clearer communication contracts, task handoffs, failure handling, and observability. A2A provides a useful framing for designing those interactions deliberately, especially when paired with patterns like MCP and implementation stacks such as Python-based agent workflows.
Key Developments
- 2026-02-13 — Andrew Ng launched A2A: The Agent2Agent Protocol, a short course created with Google Cloud and IBM Research and taught by Holt Skinner, Ivana Nardini, and Sandi Besen. This marked A2A as a named protocol and learning topic for builders exploring agent interoperability.
- 2026-05-10 — A newsletter feature highlighted a step-by-step guide for building Python-powered multi-agent systems from scratch, using MCP and A2A patterns to incrementally add complexity and enable collaboration across agents. This positioned A2A as a practical architecture pattern, not just a conceptual protocol.
Relevance to AI PMs
- Designing multi-agent workflows: A2A helps PMs break complex user jobs into cooperating agent roles, such as planner, researcher, executor, and reviewer. This is useful when a single-agent experience becomes brittle, slow, or difficult to scale.
- Defining product and system contracts: A2A pushes teams to specify what agents send each other, what context is preserved, when handoffs occur, and how failures are surfaced. PMs can use this to turn vague orchestration ideas into concrete requirements for engineering teams.
- Improving reliability and observability: In multi-agent products, errors often happen during delegation or context transfer rather than final generation. A2A gives PMs a lens for instrumenting message flows, measuring handoff quality, and deciding where human review or guardrails are needed.
Related
- Andrew Ng — Helped bring A2A into wider view through the launch of a dedicated Agent2Agent Protocol course.
- Google Cloud — Collaborated on the A2A course, signaling enterprise and platform interest in agent interoperability patterns.
- IBM Research — Also collaborated on the course, connecting A2A to more formal research and systems thinking.
- MCP — Frequently mentioned alongside A2A as a complementary pattern for building more capable agent systems; MCP typically focuses on model-to-tool or model-context interactions, while A2A focuses on agent-to-agent coordination.
- Python — Highlighted as the implementation language in the newsletter’s multi-agent systems guide using A2A patterns.
- Multi-agent systems — The broader architectural category where A2A is most directly applicable, especially when multiple specialized agents need structured collaboration.
Newsletter Mentions (2)
“#8 𝕏 Santiago showcases a step-by-step guide for constructing Python-powered multi-agent systems from scratch, leveraging MCP and A2A patterns to incrementally add complexity and enable collaborative AI agents.”
GenAI PM Daily May 10, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 11 insights for PM Builders, ranked by relevance from X, Blogs, and LinkedIn. PromptLayer’s multi-step agent evaluation framework #1 𝕏 Jason Zhou launched `/goal` support in CodeX and Hermes agents for one-step autonomous coding, advising use of interview mode, clear stop conditions, and a goal-buddy to manage state and goal files. #2 📝 PromptLayer Blog What Is Agent Evaluation? A Practical Guide for AI Teams - Agent evaluation tests whether an AI agent reliably completes tasks across real inputs, edge cases, and new versions by scoring not just final outputs but multi-step behavior via black-box, trajectory, and component-level evaluations, using metrics like task completion rate, tool selection accuracy, unsupported-claim rate, latency/cost per step, and regression pass rate. PromptLayer offers tracing with span-level context, reusable datasets, batch evaluations, backtesting, regression testing, automated evaluation triggers on new prompt versions, and flexible pipelines including code execution, human input, conversation simulation, regex checks, and LLM assertions. #3 in Udi Menkes built his new product’s entire data flow in a single interactive HTML file—complete with diagrams, in-page navigation, and color-coded complexity—letting his team understand it in minutes instead of hours. #4 𝕏 Garry Tan suggests diagramming your AI agent codebases and architecture in plain ASCII, then relentlessly questioning each component to clarify design and accelerate product development. #5 𝕏 Boris Cherny says Claude Code’s switch to a native installer means npm-only stats undercount its real usage. On Thursday it hit its second-highest signup day ever with 15× growth since Jan 1—now you can ask Claude to debug your SQL. #6 𝕏 Boris Cherny is enhancing Claude Code’s UX for snappier performance and adding debug logs so users can self-serve hang diagnostics. #7 𝕏 Harrison Chase calls LangSmith an org-wide platform for building AI agents that speeds up cross-functional collaboration and tightens feedback loops. #8 𝕏 Santiago showcases a step-by-step guide for constructing Python-powered multi-agent systems from scratch, leveraging MCP and A2A patterns to incrementally add complexity and enable collaborative AI agents. #9 𝕏 Garry Tan spends $2K/mo on Openclaw AI tokens to turbocharge product development and startup insights. He’s “tokenmaxxing” now with a goal to make these capabilities affordable for everyone in 18 months. #10 𝕏 Harrison Chase argues that treating AI agents as systems to measure and iteratively improve isn’t just a technical challenge—it demands intentional human collaboration and team processes. #11 in Peter Yang warns that unedited AI-generated markdown can compound small errors over time—what starts as 5% “slop” quickly balloons into an overwhelming pile of confusing, unverified content. Found this valuable? Share it with another PM - they can subscribe at genaipm.com Unsubscribe • Switch to Weekly
“Andrew Ng launched A2A: The Agent2Agent Protocol, a short course built with @googlecloudtech and @IBMResearch and taught by Holt Skinner, @ivnardini, and Sandi Besen.”
GenAI PM Daily February 13, 2026 GenAI PM Daily 🎧 Listen to this brief 3 min listen Today's top 25 insights for PM Builders, ranked by relevance from Blogs, X, YouTube, and LinkedIn. OpenAI Introduces GPT-5.3-Codex-Spark Model #1 📝 OpenAI News Introducing GPT-5.3-Codex-Spark - Announces the GPT-5.3-Codex-Spark product release, highlighting new Codex-powered capabilities for developers and product teams. The post introduces the model and its intended use cases and availability. Also covered by: @Simon Willison #2 𝕏 Demis Hassabis rolled out Gemini 3’s new “Deep Think” mode for Google AI Ultra subscribers in the Gemini App, enabling more advanced reasoning and complex problem-solving capabilities. Also covered by: @Josh Woodward , @Demis Hassabis , @Google AI, @Sundar Pichai , @Sundar Pichai #3 𝕏 Sam Altman launched GPT-5.3-Codex-Spark as a research preview for Pro today, delivering over 1,000 tokens per second with initial limitations that will be rapidly improved.
Related
MCP is a deployment and integration concept for exposing tools and workflows to AI systems. In the newsletter it is mentioned as a way to deploy an analytics tool everywhere.
AI educator, entrepreneur, and course creator. In this newsletter he is associated with a short course on efficient LLM serving.
Google’s cloud platform offering infrastructure and model hosting. In this newsletter it appears in a course with Andrew Ng and with Gemini 3.5 Flash on Vertex AI.
Systems composed of multiple cooperating AI agents, often designed to divide work and collaborate through structured patterns. The newsletter references building these systems with Python and agent-to-agent communication patterns.
A programming language commonly used for building AI systems and agent workflows. The newsletter references it in the context of constructing multi-agent systems from scratch.
Stay updated on A2A
Get curated AI PM insights delivered daily — covering this and 1,000+ other sources.
Subscribe Free