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 describes patterns and protocols for communication and collaboration between multiple AI agents.
- The concept was notably highlighted by Andrew Ng's Agent2Agent Protocol course built with Google Cloud and IBM Research.
- A2A is especially relevant when designing multi-agent products with planners, executors, reviewers, or specialized subagents.
- Newsletter coverage connected A2A with MCP and Python-based, step-by-step approaches to building multi-agent systems.
A2A
Overview
A2A, short for Agent-to-Agent or Agent2Agent Protocol, refers to patterns and protocols that let multiple AI agents communicate, coordinate, and collaborate to complete work together. Instead of treating an agent as a standalone unit, A2A frames agents as participants in a broader system where they can hand off tasks, share context, request capabilities, and combine specialized roles.For AI Product Managers, A2A matters because many real-world agent products become more useful when work is distributed across multiple components rather than forced through one monolithic agent. In practice, A2A is relevant when designing systems with planners, executors, reviewers, tool-using assistants, or domain-specific subagents. The concept also shows up alongside adjacent standards and patterns such as MCP, especially in step-by-step approaches to building multi-agent systems that add coordination gradually as product complexity increases.
Key Developments
- 2026-02-13 — Andrew Ng launched A2A: The Agent2Agent Protocol, a short course built with Google Cloud and IBM Research and taught by Holt Skinner, Ivana Nardini, and Sandi Besen. This helped frame A2A as a recognizable protocol/pattern for structured agent collaboration.
- 2026-05-10 — A newsletter mention highlighted Santiago's step-by-step guide for building Python-powered multi-agent systems from scratch, using MCP and A2A patterns to incrementally add complexity and enable collaborative AI agents.
Relevance to AI PMs
1. Designing multi-agent product architectures A2A gives PMs a way to think about when one agent should delegate to another. This is useful for products that need separate roles such as planning, retrieval, execution, verification, or customer-facing interaction.2. Defining interfaces between agents
As teams move from demos to production, agent collaboration needs clearer contracts: what information gets passed, when handoffs happen, how failures are handled, and which agent owns final decisions. A2A is relevant to product specs because it pushes these interface decisions upfront.
3. Incrementally increasing system complexity
The newsletter context positions A2A as part of a step-by-step build path for multi-agent systems. For PMs, that is tactically useful: start with a single-agent workflow, then introduce specialized agents only where they improve reliability, speed, or maintainability.
Related
- Andrew Ng — Helped popularize A2A through the launch of the Agent2Agent Protocol course.
- Google Cloud — Collaborated on the course introducing A2A, signaling enterprise and infrastructure relevance.
- IBM Research — Co-developed the educational launch around A2A, connecting the concept to formal research and applied systems design.
- MCP — Often mentioned alongside A2A in agent system design. MCP focuses on structured access to tools and context, while A2A focuses on communication and coordination between agents.
- Python — Referenced in the newsletter example as the implementation language for building multi-agent systems that use A2A patterns.
- Multi-agent systems — The broader category that A2A supports; A2A is a communication/collaboration pattern inside these systems.
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
A protocol for connecting AI models and agents to external tools and context. In the newsletter it appears as a building block for multi-agent systems.
An AI educator and founder known for teaching practical AI application-building skills.
Google’s cloud platform used here for project-scoped access control around Gemini API keys. For PMs, it reflects enterprise-grade collaboration and permissioning.
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