Agent Experience

An independent field guide to Agent Experience

Agent Experience research, design, and engineering.

From human intent to verified outcomes: practical guidance for the tools, documentation, workflows, approvals, recovery paths, and evaluations that AI agents rely on.

Start with the guide

Explore all guides, examples, and work →

Written and curated by Himadri Mishra.

The starting point

Good models still need well-designed products.

AX looks at how an agent discovers a capability, understands the instructions, gets authority, executes safely, reports evidence, recovers from uncertainty, and hands work back to a person.

Explore the AX framework

A few places to begin

All guides
Tools & APIsTool descriptions are product surfacesHelp an agent understand when a tool fits, when it does not, and how to recover from a bad input.WorkflowsKeep context through the handoffCarry the task, the decisions, and the next useful step forward.EvaluationFind the next thing to improveUse a public rubric for reviewing the surfaces your agents depend on.

Inspect the public work

Selected public workSee inspectable artifacts behind this field guide, including the site MCP, rubric, fixtures, and public source library.Worked examplesStudy synthetic AX workflows with state flows, deterministic tests, and explicit limits.

Keep exploring.

Find reusable resources, public guides, and agent-facing artifacts without starting from a sales page.

Browse the resources

Use the guides in your assistant.

Connect the public MCP server to search the guides, retrieve the rubric, and run a bounded catalog diagnostic.

Connect to the MCP

Common questions

Read the full definition
What is Agent Experience?

Agent Experience, or AX, is the product experience an AI agent has while doing work for someone: understanding a task, finding a capability, using it with the right context, recovering from uncertainty, and handing work back well.

How is Agent Experience different from UX and DX?

UX focuses on a person’s experience of a product. DX focuses on the developer experience. AX focuses on the product surfaces an AI agent relies on while acting on behalf of a person. The disciplines overlap, but each asks different design questions.

What should a team improve first?

Start with one real workflow. Find the moment where an agent cannot discover the right path, choose a tool, retain context, recover safely, or make a decision the team can explain. Improve that surface before expanding scope.

What makes a product easier for AI agents to use?

Clear purpose, stable structure, legible documentation, distinct tool descriptions, bounded workflows, meaningful approvals, useful recovery paths, and evaluation that shows how the result was reached.