How to Use AI and ChatGPT for Efficient UX Research in 2026

You'll be integrating powerful AI tools like Claude, Gemini, ChatGPT and/or others, into a real-world UX research scenario every step of the way. You'll design a customer interview script leveraging AI, run the interview, analyze the results, and share your insights.

Here's how it will go:

1. Identify a Research Topic: Think of a product, service, or user experience you want to research. It could be something you're working on professionally or a personal interest.

2. Create Your Interview Moderation Guide: From a list of objectives and following the framework from the class you will create your moderation guide with a little help from an AI tool of your choice (incl. ChatGPT, Claude, and Gemini)

3. Run the Interviews: Using your moderation guide conduct at least one user interview. You can use friends, colleagues, or online volunteers as your interviewees.

4. Analyze and Synthesize: Transcribe using AI tools, review the responses collected, use AI for data analysis and synthesis, and uncover the key insights from your interviews.

5. Share Your Findings: Prepare a brief report or presentation summarizing your research findings using AI to summarize and refine.

Understand how UX research has evolved over 70 years, why AI is the latest inflection point, and what separates useful AI-assisted findings from confident-sounding guesses.

In this lesson, you'll learn the fundamentals of UX Research: what it is, why it matters, and how the process works from planning through to sharing findings. We'll focus on exploratory research and introduce modern practices like continuous discovery and mixed methods. You'll also learn where AI can help speed up your work—and where human judgement still matters most. By the end, you'll be ready to run research that's both fast and credible.

This lesson teaches you how to use AI as a practical research tool whilst maintaining research quality and rigour. You'll learn what large language models actually are (and aren't), the three most common ways AI fails in research contexts, and a simple four-step quality loop—Draft → Critique → Verify → Document—that you'll use throughout the entire course. The lesson also covers how to evaluate and choose AI tools for specific tasks using a practical test-drive method, and introduces a basic safety routine for working with participant data. By the end, you'll understand how to use AI to speed up your work without compromising on evidence or credibility.

In this lesson, you'll learn how to use AI to move from a messy project brief to a clear research plan. I'll show you how to create a sanitised context packet, generate focused kickoff questions, and identify assumptions and unknowns before you recruit participants. You'll walk into your kickoff meeting prepared, confident, and in control—with AI handling the heavy lifting so you can focus on what matters: running great research.

In this lesson, you'll learn how to use AI to draft a research screener that finds the right participants whilst avoiding bias, leading questions, and unnecessary data collection. We'll cover how to create a first-pass screener with tools like ChatGPT, then run a quality assurance pass to check for inclusion risks, data minimisation, and disqualifiers. You'll also learn when not to use AI for recruitment copy, and how to apply a human QA lens to protect the quality of your participant pool.

This lesson covers how to prepare for and conduct user interviews using AI as a drafting and practice tool. You'll learn to create a moderation guide with proper consent language, question hygiene, and flow—then use AI roleplay to sharpen your interviewing skills.

This lesson teaches you how to analyse interview transcripts with AI assistance whilst maintaining rigour and traceability. You'll learn a practical workflow that prioritises evidence over interpretation, treats one interview at a time as the robust default, and uses AI to accelerate—not replace—your judgement.

We cover data handling and redaction, transcription choices (including using what you already recorded with), how to conduct interviews with the transcript in mind, building an evidence table that keeps you honest, asking AI analysis questions with guardrails, and communicating confidence levels that are credible and useful.

The approach is designed for researchers who want to work faster without sacrificing credibility, and who understand that the goal isn't a smooth story—it's insights you can actually defend.

Turn your research themes into evidence-backed insights and opportunities. Learn how to use AI to suggest ideas whilst maintaining rigour—every opportunity must map back to real quotes, and contradictions stay visible.

This lesson moves ethics from abstract principle to practical checkpoint. We cover what's safe to share with AI tools (and what's not), how to disclose AI use clearly to participants and stakeholders, and how to reduce common harms: privacy leaks, biased outputs, overconfident nonsense, and fabricated evidence. You'll learn lightweight "ethics gates" you can drop into your workflow — from planning through to reporting — plus how to keep an AI usage log so your work stays reproducible and trustworthy. The goal is simple: use AI to move faster, and keep your hands on the steering wheel so the work stays credible.