Uncovering
UX · AI Audit
Uncovering is a specialized audit of the experience in your product's AI layer.
Discover what isn't working, why, and how to fix it.
The problem
You shipped an AI feature and something's off.
- —Users aren't adopting it the way you planned.
- —You sense the experience isn't building trust.
- —The metrics aren't what you expected, and you can't tell why.
- —Users try it but don't find the value.
The problem is rarely the model. It's how the experience is designed — and the architecture decisions behind it.
The solution
A specialized audit of your product's AI experience.
Not just a UX audit. A focused look at the design and architecture decisions that lets us identify the friction points holding back adoption.
What I analyze
AI lives inside an experience, and we look at it from both angles.
UX from the AI
- ·Onboarding and feature discovery.
- ·How it's presented to the user and where it lives within the product.
- ·Human-AI handoffs.
- ·Human in the loop: when and how the user can intervene.
- ·Memory and per-user personalization.
- ·Trust signals: how the product communicates certainty, uncertainty, and limits.
AI from the UX
- ·Flows, interactions, tone, and failure modes.
- ·Coherence over time: whether the agent remembers, forgets, or contradicts itself in ways that confuse users.
- ·The gap between what the AI can do and what the interface allows.
- ·Adoption friction: where users abandon, avoid, or distrust the system.
How I audit
An audit that goes deep.
- ✓Free exploration by every relevant role: operator, manager, admin.
- ✓Directed use cases: 8 to 15 representative tasks of real use, walked through systematically.
- ✓AI-specific adversarial tests: ambiguous inputs, contradictions, edge cases, system-breaking attempts.
- ✓Review of the experience around the AI: onboarding, discoverability, integration with the rest of the product.
- ✓Shallow review of AI architecture decisions: how they impact the consistency, limits, and reliability of the experience.
- ✓Granular documentation of each finding: evidence, severity, and concrete recommendation.
Deliverables
What you receive at the end of the process.
Prioritized report
Findings ordered by impact, with concrete next steps for each.
Live walkthrough
We walk through the findings together. You ask questions, we discuss, we adjust. Your team leaves with clarity.
Functional prototype (when applicable)
Built with the actual model. Clickable. Real behavior. So you see the recommendation before implementing it.
How it works
From the first call to the results.
Scoping call (free, 30 min)
We talk about the product and the problem. I confirm whether the audit fits and whether prototype applies.
Proposal and kickoff
Within 24-48 hours you receive the proposal with scope and timeline. On signing, we start.
Audit
I investigate the product in depth: flows, user experience, and AI layer.
Delivery
Report, live walkthrough, and prototype when applicable.
Follow-up (included)
One week of email support for any questions that come up after delivery.
Why me
UX and AI architecture, at the same time.
20+ years
Designing and building software.
8 years
UX as an explicit discipline.
AI + product
My current focus, at the intersection of both.
I design and implement AI systems. That's exactly what lets me audit from the inside — from the experience and from the architecture at the same time.
See case study → →Did you ship AI but users aren't trusting it?
Let's find out what's holding back adoption and how to fix it.