AI UX Design

Designing AI Products People Can Understand and Trust

Most AI features fail the same way: they hide their reasoning, offer no way to correct a wrong output, and fail silently when they're unsure. I design AI products the other way, with output people can see through, edit, and trust incrementally as it proves itself. I'm an AI UX designer based in Kathmandu, Nepal, currently leading design for Decisions AI, an enterprise AI meeting assistant used inside Microsoft Teams by 5,000+ organizations.

Principles

How I Design AI UX

Confidence & Uncertainty

Surfacing how sure the system is, not just its output. A confident-sounding wrong answer is more dangerous than one that visibly hedges: the interface should show its work.

Editable AI Output

AI-generated content is a draft, not a decision. Every output needs a clear, low-friction path to correct it before it becomes the record of what happened.

Human Review

For anything consequential (a decision, a vote, a commitment) a person confirms it. AI accelerates the path to that moment; it doesn't replace it.

Explainability

If a user can't tell why the system produced a given output, they can't trust it or correct it. Explaining the “why” is part of the interface, not a debug log.

Failure & Fallback States

AI features fail differently than normal software: confidently, silently, or in ways that look like success. Designing the failure states matters as much as the happy path.

Progressive Trust

Nobody hands full autonomy to a new feature on day one. Trust is earned in stages, starting with suggestions a human approves and expanding scope as the system proves reliable.

Enterprise AI Constraints

Enterprise AI adds compliance, audit trails, and NDA-covered data most consumer AI patterns ignore. The design has to hold up under review, not just a demo.

Applied in Production

Enterprise AI, Not a Demo

Decisions AI runs inside Microsoft Teams for 5,000+ organizations, spanning enterprise, healthcare, and government bodies. Every AI-generated summary or suggested action needs a clear confidence signal, an easy way to correct it, and a human still making the actual decision. It's an active, NDA-covered engagement, so what's shared here is limited to what's publicly verifiable and a direct account of the design constraints, not internal research or metrics.

Decisions (active client project, NDA-covered) · 2019–Present

Decisions AI

Lead Product Designer for Decisions AI, the mobile companion to an AI-powered Microsoft Teams meeting platform used by 5,000+ organizations spanning enterprise, healthcare, and government. Active NDA-covered project — no internal research, usage data, or design rationale shared here, only what's publicly verifiable plus a direct account of the role.

EnterpriseLead Product Designer

Writing on AI UX and Product Design

Agent UX

From UX to AX: How Experience Design Is Evolving From Users to AI Agents

UX isn't being replaced; the user is expanding. How design moved from screens people operate, to AI people steer, to products AI agents use for them.

Oct 7, 202618 min read

Beyond the Chatbot: The AI UX Design Patterns That Actually Work

Most AI features are a sparkle icon nobody uses. The ones that change behavior follow different patterns — pre-fill, visible confidence, graceful failure.

Aug 10, 20268 min read

Agent UX

What Is Agent UX? A Framework for Where AI Is Reshaping Product Design

UX isn't being replaced by AI. It's growing a third layer: Agent UX. A working model for what each layer covers, and why it catches most teams unprepared.

Aug 12, 202610 min read

Designing Trust Into AI Features: Why Explainability Beats Accuracy

Users don't trust AI because it's accurate. They trust it because they can see why it did what it did. A framework for designing calibrated trust into AI features.

Sep 18, 20267 min read

Agent UX

The AI Agent Glossary Every Designer Needs in 2026

Agent, orchestration, grounding, guardrails — agentic AI vocabulary is spreading through product meetings. Here's what each term means for design work.

Aug 18, 20268 min read

Where AI Actually Fits in the Product Design Process

A phase-by-phase look at where AI genuinely speeds up product design inside the Double Diamond, and where human judgment still has to lead.

Aug 10, 20269 min read

Forget AI Tools. Master These 7 AI Concepts Instead

Tool debates burn out fast. The mental models underneath don't — the concepts that separate designers who work well with AI from those who just use it.

Jul 7, 20269 min read

Scaling Product Design With AI and Just Enough Technical Skills

Too much to build, not enough dev bandwidth. Here's the five-part system — AI tools plus just enough technical skill — I use to close that gap myself.

Aug 10, 20267 min read

The New Handoff: From AI-Generated UI to Production-Ready UI

AI shortened the path from idea to interface, but the design-to-dev handoff didn't disappear — it moved downstream, into code review.

Jul 10, 20265 min read

See all AI Product Design articles

Building an AI feature people will actually trust?

If you're designing AI into a product and want the trust, failure states, and human oversight handled properly from the start, I'd love to hear about it.

Get in Touch