We want our software to be easy for people to use. That means building a great UI. Now that people work with AI agents, we need our software to be easy for agents to use. That means building a great MCP. Model Context Protocol servers give AI agents fingers to feel around and act in the world, one tool at a time.

In this session, I’ll share design considerations from the Honeycomb.io MCP. I’ll contrast MCP design with human UX and software APIs, then discuss ways to tell whether the MCP is effective in production.

In this talk, we're unpacking GraphQL Fusion, a new approach that makes building distributed GraphQL APIs easier. We'll explore how this approach lets your teams work independently by owning different parts of the company's graph and cover how you can reshape subgraphs to follow your company's rules. Come learn about this powerful tool that brings efficiency and customization to your GraphQL operations.

A new standard is here too make it easier to share resources cross boundaries and bring about the agentic era.