Agentic Design Research
Research is where agents quietly do their best design work: gathering, structuring, and synthesising evidence at a scale a single researcher cannot, while the researcher keeps ownership of questions, interpretation, and ethics. This course covers research packets as the unit of agentic research, deep desk research and competitive teardowns, synthesis across interviews and tickets, surveys, experiments and funnel diagnosis, journey maps and service blueprints generated from product data, and the step most research decks skip: turning insight into briefs that change what gets built.
Modules6 modules
Last updated2026-06-02
Audience and outcomes
UX researchers, product designers who carry research as part of their role, and design leads who need evidence to move faster without becoming shallower.
- Structure research as packets — question, sources, method, findings, evidence — that agents can build and humans can audit.
- Run deep desk research and competitive teardowns that cite their sources and separate observation from inference.
- Synthesise interviews, support tickets, and open-text feedback into themes with traceable evidence.
- Use agents for survey design, experiment readouts, and funnel diagnosis without laundering weak data into confident claims.
- Generate journey maps and service blueprints from product data and keep them current.
- Convert findings into design briefs so research changes what gets built rather than what gets presented.
Modules
Modules marked Available have full slide decks with speaker notes and narration scripts. The rest show their planned outline until production catches up.
Research Packets
The unit of agentic research: a packet that holds the question, the sources, the method, the findings, and the evidence trail — built by an agent, auditable by a human, and reusable as briefing input for design work.
- Structure a research packet so the question, method, and evidence are inspectable.
- Decide which research activities agents do well and which corrupt without human contact.
- Set source and citation standards before the first packet is built.
Deep Design Research and Competitive Teardowns
Desk research and competitive analysis run at agent scale: structured teardowns of competitor flows, pattern surveys across a category, and the discipline that separates what was observed from what is being inferred.
- Scope a deep research run so breadth does not become unfocused accumulation.
- Run competitive teardowns that capture flows, patterns, and trade-offs with screenshots.
- Keep observation, inference, and recommendation visibly separate in the output.
Research Synthesis with Agents
Synthesis across interviews, support tickets, reviews, and open-text feedback: theming with traceable evidence, contradiction-hunting, and the human interpretation pass that decides what the themes mean.
- Prepare qualitative data so an agent can theme it without flattening nuance.
- Require every theme to trace back to specific quotes and sources.
- Run the human interpretation pass: what the themes mean and what to do about them.
Surveys, Experiments, and Funnel Diagnosis
Quantitative work where agents help with design and analysis but cannot supply rigour: writing surveys that do not lead, reading experiment results without inventing significance, and diagnosing funnel drop-off with hypotheses tied to evidence.
- Use agents to draft and critique survey instruments against known bias patterns.
- Read experiment results with an agent without overstating what the data supports.
- Run funnel and drop-off diagnosis that produces ranked, testable hypotheses.
Journey Maps and Service Blueprints from Product Data
Journey maps and blueprints built from what the product actually records — events, tickets, session paths — rather than workshop recollection, and kept current by re-running the generation instead of redrawing the poster.
- Generate journey maps from event and support data with the gaps marked honestly.
- Extend journeys into service blueprints covering front-stage and back-stage steps.
- Keep maps current as living artifacts rather than one-off workshop posters.
From Insight to Brief
The step that determines whether research mattered: converting findings into design briefs with the evidence attached, prioritising what to act on, and closing the loop so the next research question comes from what shipped.
- Convert a research finding into a design brief that carries the evidence with it.
- Prioritise findings by decision impact rather than by how interesting they are.
- Close the loop: track what shipped because of the research and what it changed.
Books and articles behind this course
The course teaches the practice; the books and articles carry the depth, the sources, and the worked runs it draws on.
The operating model for product designers, design leads, and builders who need to understand what changes when agents join design work.
- Brief an Agent Like a Design Partner
A practical workflow for turning a loose design request into a reviewable agent brief — with a traced run on this site's own field-notes page, real plan-mode guidance for Claude Code, Codex CLI, OpenCode, and Gemini CLI, and the templates to reuse the same day.
- Research Packets for Agentic Design
A practical editorial system for turning tool changes, reader questions, screenshots, examples, and experiments into durable agentic-design curriculum.
- Four Agentic Design Workflows in Production: What Actually Happened
Four real agentic design workflows traced from their own repositories — an editorial site, a multi-agent book pipeline, a book-to-video pipeline, and the design system underneath the site — with the timelines git can prove, the configs that did the steering, the failures the gates caught, and the patterns that repeat across all four.