Building AX evals that actually work
This is the eighth and final article in a series about Agent Experience (AX): the practice of making AI coding agents work correctly with your technology. The series covers what you can and can’t…
Read the full articleYou might also wanna read
The Rise of Agentic Experience (AX) Design: Moving Beyond Human-Facing UX
As AI agents quietly take over workflows, a new discipline is emerging: AX (Agentic Experience) Design. The designers who thrive in the next
Webdesigner Depot·21d agoThe Rise of Agentic Experience (AX) Design: Moving Beyond Human-Facing UX
As AI agents quietly take over workflows, a new discipline is emerging: AX (Agentic Experience) Design. The designers who thrive in the next
webdesignerdepot.com·21d ago
agent-skills-eval: An open-source test framework for measuring AI agent skill effectiveness
A test runner for agentskills.io-style AI agent skills - darkrishabh/agent-skills-eval
GitHub·2mo ago
Your AI Agent Passed Evals. That’s the Problem.
Passing evals doesn’t mean your system works. It means your tests didn’t catch how it fails.
I Built an AI Agent Team That Fixes Its Own Mistakes — Here’s the Full, Tested Code
Most agent tutorials show you the happy path. This one shows you what happens when an agent fails — and how to make the system heal itself…
Developer experience is dead. Long live agent experience.
Developer experience is giving way to agent experience: context, deterministic environments, verification, and safety for reliable AI coding
The Essential Role of Manual Data Review in AI Agent Evaluation
No amount of evals will replace the need to look at the data, once you have a evals good coverage you’ll be able to decrease the time but it
Comments
Sign in to join the conversation.
No comments yet. Be the first.