UXPALOOZA - Agent Readiness Testing — Llewyn Paine Consulting, LLC

Welcome, UXPALOOZA ATTENDEES!

Can an AI agent figure out your website?

Give us your task, and we’ll send you a video of an agent attempting it on your website.

What will my video look like?

Your video will show one agent attempting to complete a task online following the instructions you provided. Watch an example below!

Why test agent readiness?

AI agents are the new mediators of user experience. When your user sends an agent to your website, and it is unable to complete its task–it’s your user who gets frustrated.

Agent and bot traffic surpassed humans online for the first time this year,* and as more users adopt agents like Claude Code and Muse, they’ll become an increasingly important vector of UX. But we’re already feeling their impact today–last year AI and agents influenced $67B in sales during Cyber Week alone.*

How many runs do you need for your agent readiness test to be reliable?

It depends how variable the agent is. Some agents perform roughly the same every time, while others make wildly different mistakes across different runs. By default, I run tests 11 times per agent. This gives a naive probability of encountering the most common issues with roughly 95% confidence

Can we use your platform to test our interface for AI agents?

Absolutely! The single run we’ll send you here shows you what happened for one agent, one time. The complete test gives you the bigger picture, revealing more agent friction points your real users are most likely to encounter. Eleven runs, a human-written report with findings, severity, business impact, and engineering-ready recommendations–plus, a representative session recording, for $799. Share this with your product lead or VP if your team needs the full report.

What’s the best agent to use for testing?

The best agent to test your website is the one your user uses!

That said, different agents use different technological methods to “see” and interact with your website, and different models (LLMs and VLMs) can have drastically different performance. So to cover your bases, it’s safest to test across a variety of different agents and models.

Need comprehensive, cross-agent testing? For teams that need to test across multiple agents, multiple models, or dozens of runs we offer custom engagements. We run the matrix manually using documented methodology and deliver prioritized recommendations. Contact me to discuss scope.

Where can I download the slides from your UXPALOOZA talk on agent readiness?

They’ll be uploaded here within a few days.