UX Design · research · 2026

Microsoft Foundry AI model discovery experience

Usability Research for an AI Developer Platform

Over Spring 2026, I researched Microsoft Foundry, a comprehensive hub for developers to deploy and experiment with AI agents. Throughout the project, I collaborated with the Microsoft Core AI team to identify key usability issues and deliver design recommendations.

At the end of the project, our team presented design recommendations based on user research insights to 30+ Core AI researchers, designers, and engineers. These recommendations directly informed the next iteration of Microsoft Foundry, which has since impacted more than 80,000 users.

Role: UX Researcher
Timeframe: Jan 2026 – Mar 2026
Tools: QualtricsUserInterviewsUserTesting
Collaborators: Microsoft Core AI TeamHCDE Master’s students

01 What is MS Foundry?

A comprehensive platform for AI agent deployment

Microsoft Foundry (formerly known as Azure AI Studio) is Microsoft’s unified, enterprise-grade platform for building, deploying, and managing AI applications and intelligent agents.

02 Research methodology

Mixed user research method

Duration

60 minute sessions

Format

Virtual moderated test

Method

Structured interview & direct observation tasks

Measurement

Post task questionnaire

03 Participant Demographic

AI developer and software engineer who has a thorough understanding of AI agent development process

Target users: 4 students and 4 industry professionals with shared software development and generative AI experience

04 Goal

Our study began by translating the business objective North Star Metric into research goals

Business goal

Increase conversion rate by helping users confidently identify and select the model that best fits their needs.

Research goal

Navigation

Understand how users navigate the platform and where they’re drawn to

Discovery

Evaluate how users determine the most suitable AI model and points of friction

Comparison and understanding

Understand how users evaluate and compare model information

User experience and aesthetics

Assess satisfaction with the discovery experience and the efficacy of the redesign

05 Findings

To help the Core AI team better prioritize improvements, our team organized usability issues into high-, medium-, and low-priority, and paired each one with a design recommendation that directly impacted the next version of Foundry.

High priority #1

Low discoverability of “Ask AI” tool

Many treated “Search with AI” as a standard search bar, missing the capabilities of an AI assistant in “Ask AI”.

4 out of 8 used keyword searches (e.g., “Models,” “Chatbot”).
1 of 8 interacted with the “Ask AI” chat icon next to the search field.

Microsoft Foundry home screen showing Search with AI and Ask AI entry points

Solution

More intentional design for the search bar and AI features.

Better support traditional search functions.
Call more attention to AI agent.

Before

After

Foundry home with a more prominent search bar and a floating Ask AI widget

High priority #2

The “Compare Models” feature was generally easy to use — once found

This chart covers how long it took participants to find the comparison page after being prompted to compare two models. On average, it took 60 seconds to locate the "compare models" feature.

For five of our participants, it took under 20 seconds for them to locate Compare Models. However, two participants, participant 4 and 7, took 3 minutes to locate the compare models feature. One participant, participant 3, never found the compare models screen.

How long did it take participants to find “Compare Models”?

Time taken

Average

P10:10

P20:10

P3N/A

P43:00

P50:18

P60:13

P73:07

P80:02

050100150200

Time (In Seconds)

But why did it take some participants longer than others? It mainly depends on what screen they start searching from.

How long did it take participants to find “Compare Models”?

Time taken (on average)

Started from models page0:10

Started elsewhere1:37

050100150200

Time (In Seconds)

Solution

Surface Compare Models CTA to more screens (especially to Model Specifications) for greater accessibility.

Before

Model specifications header without a Compare models action

After