Beyond Prompting: Build reusable AI workflows for UX research.
A 7-week live online course for mid-career to senior UX researchers and research managers who want to build durable AI systems, not starting from scratch on every project.
- Investment
- $695
- Format
- Live online · 7 weeks
- Cohort size
- Capped at 15
Lifetime access to recordings and materials
Revisit every session and resource, for good.
Full refund up to the first day of class
Change your mind any time before week one.
Certificate of completion
A shareable credential when you finish.
You can already get an AI to help you. The hard part is building a practice that doesn't start over every time.
You're prompting on every project. Some of it works well. But when the project ends, so does the system you improvised. The next project starts fresh: new context, new instructions, the same setup work you did three months ago. Meanwhile, someone in your org is already asking what your team's AI strategy for research looks like. You have tactics. What they're asking for is infrastructure.
The researchers who are genuinely ahead right now are not the best prompters. They're the ones who have built reusable context systems, workflow libraries, and research memory that make AI perform consistently across projects, not just on the first try. This course is about building that layer. AI does not remove the need for research judgment. It raises the premium on it.
This course teaches UX researchers how to build AI workflows for UX research that are durable, reusable, and function-level rather than project-level. You'll move from understanding how LLMs actually behave through building project context files, research memory systems, and reporting infrastructure, so you can become the person in your organization who builds AI into research sustainably, not just uses it personally.
The course runs over 7 weeks, live online, with a hands-on exercise in every module that builds toward the capstone: a practical AI infrastructure plan you take back to your own research function. Each module builds on the last, moving from individual context systems to team-level repositories, planning workflows, and full research function strategy. The approach is systems-first and judgment-centered. This is not a prompt-template library or a tool tour.
- 01
Build reusable context systems and project memory so AI produces consistent, high-quality support across projects.
- 02
Create workflow libraries for research planning, synthesis, and reporting that your team can adopt and improve over time.
- 03
Evaluate AI tools against real quality, privacy, and workflow criteria, not vendor marketing claims.
- 04
Write a practical AI strategy for a research function that you and your org can implement right away.
- 05
Apply synthetic users and simulated data responsibly as planning and stress-testing tools, and explain precisely where they stop being useful evidence.
How will this AI workflows course help your career?
Lead AI strategy decisions for the research function
When a senior leader asks what your team's AI strategy for research looks like, you'll have a structured answer: context systems, quality standards, tool criteria, and adoption principles. Researchers who can build and articulate that strategy get included in the decisions that shape how the whole organization uses AI.
Develop end-to-end AI research infrastructure competency
Most researchers pick up AI skills tool by tool, project by project. This course gives you the full pipeline: understanding how LLMs behave, building context and memory systems, organizing repositories, supporting planning and reporting with reusable AI workflows, and capping it with a function-level strategy. You'll apply it independently, not just recognize it when others do.
Demonstrate applied AI research systems expertise
Few researchers have actually built the infrastructure layer: reusable context files, workflow libraries, research memory systems, a real AI strategy for a team. The course capstone is a practical AI infrastructure plan you can show in a portfolio review, a promotion conversation, or an interview: evidence of systems thinking, not just tool fluency.
Achieve organizational authority on responsible AI adoption in research
After this course, you're equipped to review how your organization is using AI in research, flag where it's creating false confidence or methodological risk, set quality standards, and build team norms. That's the standing of a research leader who can protect rigor while helping the organization move forward.
Strengthen credibility with research leadership, ResearchOps, and cross-functional partners
Research managers, ResearchOps practitioners, and senior leaders are already asking for AI research strategy. When you speak the language of infrastructure rather than just tools, you become the researcher who helps leadership make real decisions, not the one who demos impressive prompts and leaves the hard questions to someone else.
→ Built for you if
- You're a mid-career to senior researcher, manager, or ResearchOps practitioner, and people in your organization are already asking you what the AI strategy for research should be.
- You want to build AI into your research practice systematically (reusable systems, not one-off experiments) and advise your team on how to do the same.
- You can already run research independently; you're here to build infrastructure around it, not learn the fundamentals.
× Not the right fit if
- You're new to UX research. This course assumes you can plan and run studies on your own. Start with research fundamentals first.
- You want a prompt-template library or a comparison of AI tools. This course builds systems; it doesn't hand you shortcuts.
- You want to automate research away from researchers. This course is for people who believe AI raises the premium on human judgment.
Assumed going in
- You've planned and run UX research studies independently: qualitative, quantitative, or both.
- You understand core UXR methods well enough to evaluate the quality of AI-supported outputs.
- No prior AI expertise, coding knowledge, or Git experience required.
Helpful, not required
- You've used at least one AI tool (ChatGPT, Claude, Gemini, or similar) for any purpose, even personal.
- You have a current or recent research project or team context to bring the work back to.
01
What Researchers Need to Know About AI Before Building With It
Develop a grounded mental model of how LLMs actually behave, so you can use them without panic, denial, or hype-chasing.
- Distinguish what generative AI is genuinely good at from what it confabulates with equal confidence
- Recognize hallucination, sycophancy, and false fluency before they get into a research output
- Identify where AI raises the premium on researcher judgment, and why that premium is going up, not down
02
From Prompting to Research Infrastructure
Move from one-off prompting to reusable context systems that preserve your expertise across every project and tool.
- Build a lightweight personal Researcher SCP and project context file reusable across AI tools
- Distinguish reusable context from one-off instructions, and understand why the difference matters at scale
- Turn research domain knowledge into operational infrastructure that AI can reliably draw on
03
Repositories, Research Memory, and Versioning
Organize AI-enabled research work so it's findable, reusable, and trustworthy over time.
- Set up a lightweight research repository or workflow library structure for your practice or team
- Decide when version control (including Git) is useful for prompts, workflows, and research assets
- Maintain traceability from AI-supported outputs back to source material and original evidence
04
AI-Supported Research Planning and Decision Framing
Use AI to sharpen study framing and decision quality before fieldwork begins, without ceding researcher judgment.
- Turn a vague stakeholder ask into a clearer research question, decision, and evidence plan using AI-supported workflows
- Stress-test study designs and draft guide variants with reusable planning infrastructure
- Keep the researcher in charge of framing while AI handles drafting, exploration, and gap-checking
05
Reporting, Share-Outs, and Research Communication Infrastructure
Build reporting infrastructure that helps findings travel better without flattening nuance or breaking the chain of evidence.
- Create reusable reporting templates that turn findings into audience-specific formats for product teams, executives, and stakeholders
- Maintain traceability from claims to evidence while improving clarity and usability
- Build research communication workflows that turn one study into reusable organizational knowledge
06
Synthetic Users, Simulation, and Safe Fake Data
Apply synthetic research materials responsibly as planning and stress-testing tools, not as substitutes for real user evidence.
- Create or evaluate a synthetic dataset or simulated user scenario, then define precisely what it can and cannot responsibly support
- Distinguish imagination, prediction, and evidence when working with AI-generated research materials
- Communicate the limitations of synthetic methods clearly to stakeholders who may not know the difference
07
Building an AI Strategy for the Research Function
Articulate a practical AI strategy for a research function that a senior leader can act on, including where AI should and should not touch the research process.
- Evaluate AI tools against real criteria: quality standards, privacy and consent requirements, workflow fit, and build vs. buy tradeoffs
- Create team norms for AI-assisted research that protect rigor without creating process theater
- Write a lightweight AI infrastructure plan covering context systems, repositories, workflow templates, quality checks, and adoption principles
Aaron Kagan, PhD
Aaron has spent the better part of a decade doing the definitional work that comes before an AI product can be evaluated at all. At Google, his Choice Lab research turned an open-ended Digital Markets Act mandate into a measurable framework now used to evaluate DMA compliance across Search, Chrome, and the global virtual assistant. He built Google's Taxonomy of Social Benefits in AI for the Chief Legal Officer and wrote the standards the company uses to prevent AI products from being anthropomorphized. This work has since shaped Search's AI Mode policies. He is the author of An Introduction to Embodied Mind (Routledge, 2026) and writes the Deep Context series on AI systems, metaphor, and decision-making. Full bio →
Sessions meet Wednesdays 12–2pm EDT, August 12 through September 23, 2026. Each module includes a hands-on exercise that builds toward the capstone: a practical AI infrastructure plan you take back to your own research function.
Each session combines a short framing of the week's concept with applied work: building real artifacts like context files, workflow templates, and planning frameworks you'll use in your own practice. You're building a system, not reviewing slides.
Every session is recorded and posted the same day. The live session is where most of the building and discussion happens, but you won't fall behind if you need to catch a recording.
What is "AI infrastructure for UX research," and what will I learn? +
"AI infrastructure for UX research" refers to the reusable systems that make AI perform consistently in a research practice: context files that carry your expertise into every AI session, workflow libraries your team can use across projects, research memory that accumulates over time, and reporting templates that make findings travel better. Most researchers are prompting ad hoc, getting useful output but starting over each time. This course teaches you to build the layer underneath the prompting: the structure that makes AI reliable at scale, not just occasionally useful. Over 7 weeks, you'll build each component of that infrastructure and cap it with a function-level AI strategy you can take back to your own organization.
How is this different from the UXR Institute AI for UX Research course? +
The AI for UX Research Course teaches how to use AI to accelerate coding, synthesis, and insight generation on active research projects. It's the right starting point for researchers who want to get faster and deeper on project-level analysis. This course picks up at the layer above: once you know how to use AI productively, how do you build a practice around it? Context systems, workflow libraries, research memory, and function-level strategy. The two courses are designed to work together, not compete.
Do I need to know how to code or use Git? +
No. The course covers version control and Git at a conceptual level, enough to know when those tools are useful for a research practice, but you won't write code or commit files. The goal is judgment about when these tools belong in a research workflow, not technical fluency with them. No prior programming experience is needed.
Is this too basic or too advanced for me? +
This course is designed for researchers who can already run studies independently. If you're new to UX research, start with research fundamentals first. If you're a mid-career to senior researcher, research manager, or ResearchOps practitioner who is already using AI but hasn't systematized it, this is built for you. It assumes research competence and builds AI infrastructure on top of it.
When should AI be used in UX research versus human judgment? +
This is one of the course's central questions, and there's no single formula. As a general principle: AI handles volume, drafting, and pattern-matching well; researcher judgment is essential for framing, interpretation, reading nuance, and making calls that affect real people. The course is designed to help you build decision frameworks that answer this question for your specific context, not hand you a rule that doesn't survive contact with a real research project. Module 1 gives you a grounded model of what AI actually does; the remaining modules teach you where to put it in a workflow and where to keep it out.
Is this useful for research managers, or only for individual researchers? +
Both. Individual researchers will leave with context systems, workflow libraries, and a research repository they can use immediately. Research managers and ResearchOps practitioners will also be equipped to build team norms, evaluate tools for their function, and write the kind of AI strategy a senior leader can act on. Module 7 is specifically designed for the function-level challenge: what does a sustainable AI strategy for a research team actually include?
What tools or software will we use? +
The course is tool-agnostic by design. Concepts like context files, research memory, and workflow libraries apply regardless of whether you use Claude, ChatGPT, Gemini, or another AI system. Where specific tools appear in exercises, they're used to illustrate a principle, not to lock you into a particular vendor. You'll come out with infrastructure you can apply in whatever AI environment your organization uses.
What will I be able to do after completing this course? +
By the end of the 7 weeks, you'll be able to build and maintain reusable context systems for AI-assisted research, create workflow libraries your team can use, evaluate AI tools against real criteria rather than marketing claims, apply synthetic users and simulated data responsibly, and write a practical AI strategy for a research function. The capstone is a lightweight AI infrastructure plan you design for your own organization (a concrete artifact, not a reflection essay).
Is AI going to replace UX researchers? +
Not the premise of this course, and not what the evidence actually suggests. AI does not remove the need for research judgment; it raises the premium on it. Organizations that adopt AI in research still need someone who can frame the right question, interpret behavior in context, separate signal from noise, and help the organization make better decisions. What AI changes is the ceiling on what a researcher can produce and the baseline speed expectation. This course is about positioning yourself on the right side of that shift, as the person who builds the infrastructure, not the one who gets outpaced by it.
What's the real time commitment per week? +
The live sessions are the core of the course. To get the most out of it, students can complete the optional homework between sessions, which may add 1–2 hours on top of the session time. The exercises are designed to be applied directly to work you're already doing, so you're building real artifacts for your own practice rather than toy examples.
Will I get recordings if I miss a session? +
Yes. Every session is recorded and posted the same day. The live sessions are where most of the building and discussion happens, so attending live is worth it, but you won't fall behind if you need to catch a recording.
How is this different from a prompt-engineering course or a free resource? +
Prompt engineering courses teach you to write better instructions for an AI in the moment. This course teaches the layer above: how to build systems that carry your expertise across sessions, projects, and team members without requiring you to re-prompt everything from scratch each time. Free resources (blog posts, YouTube tutorials, LinkedIn posts) tend to cover individual tactics. This course builds the strategy that connects those tactics into a practice. The difference shows up months later: either you're still prompting each project from scratch, or you have infrastructure that compounds.
Won't using AI make my research look polished but actually be less rigorous? +
This is one of the most important concerns practitioners are raising right now, and it's exactly what the course is designed to address. CHI 2025 research on generative AI in UX research found that "people are cognitive misers: following up an LLM feels like the work is already done," which means hallucinations and thin synthesis pass through unchallenged. The course doesn't treat AI as a synthesis replacement. It treats AI as infrastructure for the parts of the workflow where it genuinely helps (drafting, structuring, surfacing gaps) and builds in the judgment practices that keep the researcher in charge of interpretation, evidence fidelity, and claim strength. Module 1 specifically covers how to recognize false fluency and fabricated outputs before they reach a stakeholder deck.
If I build AI workflows, will I be easier to replace? +
This is a real concern, and it deserves a direct answer. A UXR strategist surveyed by UXtweak in 2025 put it plainly: "They don't need us to sit around and prompt AI. They'll ask someone cheaper to do that." She's right: if AI strategy in your organization gets defined as "researchers now operate AI tools," that's a race to the bottom. This course is built on the opposite premise: the researchers who are hardest to replace are the ones who build the infrastructure layer, set quality standards, advise the organization on where AI does and doesn't belong in research, and preserve the interpretive judgment that makes findings credible and defensible. Prompting is a commodity. Building the systems, and exercising the judgment that makes those systems produce reliable research — that is not.
Enroll with confidence. Full refund right up to the first day of class. No form, no friction. Once the course starts, lifetime access to every recording and resource is yours to keep.
Build the AI research practice your organization is already asking for.
Enroll Now — Aug 12 cohort15 seats · enrollment closes when full
Loading the question form…
