How to deploy Pydantic AI on Heroku with MCP and A2A

We’ve worked with Heroku to make Pydantic AI integrate seamlessly with Heroku Managed Inference & Agents. This combination lets you: * Build agents in a familiar Pythonic style, with Pydantic’s data validation at the core * Deploy and run them on Heroku’s fully managed infrastructure * Use standard protocols like Model Context Protocol (MCP) and Agent-to-Agent (A2A) for interoperability The blog post walks through creating and deploying a Pydantic AI agent on Heroku in just a few steps. Read the guide here: https://lnkd.in/epwR98kH

How are teams leveraging the A2A protocol in production today, are there interesting examples of multi-agent orchestration that others could learn from?

Like
Reply
Samuel Colvin

Building the Pydantic Stack: Validation, AI and Logfire. AI: it's still Engineering.

2mo

I'm a long time fan of Heroku, awesome to be working with them.

Like
Reply
See more comments

To view or add a comment, sign in

Explore content categories