[agents](https://carteblanche.com/index.md?kind=agent) / [research](https://carteblanche.com/index.md?category=research)

# ux-researcher

what it does

Use this agent when you need to conduct user research, analyze user behavior, or generate actionable insights to validate design decisions and uncover user needs. Invoke when you need usability testing, user interviews, survey design, analytics interpretation, persona development, or competitive research to inform product strategy.

tools it asks for

Reads files · Uses the web

by VoltAgent · version 1 · license MIT

We imported this agent from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/ux-researcher)

Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/ed74d115b7fb7026a22a4f816a8e3250f425e3b4/categories/08-business-product/ux-researcher.md) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/ux-researcher/download)

## Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself.

[Compare the answers](https://carteblanche.com/skills/ux-researcher/compare)

## The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 7 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 7 Nov 2026

## The tasks

written by Carte Blanche

**example-1**

“We're redesigning the checkout flow for our meal-kit subscription app. Analytics show 38% of users drop off at the payment step on mobile, versus 19% on desktop. Can you write a moderated usability test plan for 6 mobile participants? Include recruiting criteria, 5 task scenarios, a few probing follow-up questions, and the success metrics we should track.”

**example-2**

“I just ran 8 interviews with freelance designers about how they track invoices and chase late payments. Key notes: 6 of 8 use spreadsheets, 5 said awkwardness about reminding clients is their biggest pain, 3 had missed tax deadlines, and 2 tried invoicing apps but quit because of fees. Can you synthesize these into 2 personas and a short list of prioritized insights we can use to shape our product roadmap?”

## Install

Download the .zip and unzip it. Put `ux-researcher.md` here:

Claude Code · `~/.claude/agents/` · Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others.

Cursor · `~/.cursor/agents/` · Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for.

Codex · Codex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there.

Keep its license file beside it, as `ux-researcher.LICENSE`: a name that doesn’t end in .md, since every .md file there is read as an agent.

Then start a new session and ask for it by name. Folders checked 6 November 2026.

Or [install from your agent](https://carteblanche.com/connect.md): ask it to install `ux-researcher` from Carte Blanche.

## Badge for your README

Carte Blanche: Verified

Paste this into the agent’s README. It links to this page, and shows how the listing stands whenever it’s loaded.

```
[![Carte Blanche](https://carteblanche.com/badge/ux-researcher.svg)](https://carteblanche.com/skills/ux-researcher)
```

## About this test

- **tested**: 7 Nov 2026
- **version tested**: v1
- **cases**: 2
- **tries per case**: 1 try per case
- **run without the agent**: yes
- **cases written by**: Carte Blanche
- **size**: 6371 characters

What this shows, and what it doesn’t

How 2 models answered these 2 requests, with and without the agent. It says nothing about other models, and it doesn’t limit what your own agent can do.

The answers were written without tools: the agent’s instructions were the system prompt, and it read no file and ran nothing.

[How we test](https://carteblanche.com/how-it-works.md)
