Skip to content
Sign in
Agentic Design Research

Run research packets agents can build — and humans can still audit.

Research is where agents quietly do their best design work: gathering, structuring, and synthesising evidence at a scale a single researcher cannot. They can speed screening and synthesis. They do not replace participants, and synthetic users are not a substitute. 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.

Pay once. Yours to keep, with updates.

US$39One-time purchase

Buy courseDesigner TrackEverything bundle

Buying for a team? Team seats

Modules
6 modules
Total time
≈4h 35m
Last updated
2026-10-09

Curriculum

6 modules

Slides are the lesson; study guide and transcript come with each module.

Time commitment

≈4h 35m

About ≈5 hours across the full outline — work at your pace.

Access

US$39

Pay once. Yours to keep, with updates.

What you will build / 01

Artefacts you can take back to the team.

Desk research, teardowns, synthesis, surveys and funnels, journey maps from product data, and briefs that change what gets built. Synthetic users stay labelled.

01

Research packets with question, sources, method, findings, and evidence

02

Cited desk research and competitive teardowns

03

Interview and ticket synthesis with traceable themes

04

Survey, experiment, and funnel readouts that do not launder weak data

05

Journey maps and blueprints kept current from product data

06

Insight-to-brief handoffs that change the backlog

Stepped cream research cards, cobalt accent card, yellow pencil, and cream sheet with a cobalt arrow on warm paper
Curriculum / 02

Module outline

Open the first module you have not finished. The slides are the lesson. The study guide and the transcript are the same module if you would rather read.

01

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.

02

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.

03

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.

04

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.

05

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.

06

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.

Inside the materials / 03

Sample lesson & slide previews

Titles and diagrams from early modules — the same materials you open after checkout.

Six cards show the parts of a research packet — question, sources, method, findings, evidence trail, and open questions with the decision — with arrows pointing down to what each part does after the run: the question scopes later runs and briefs, sources are re-checked when the packet is regenerated, the method lets a reviewer audit or re-run the work, findings become constraints in design briefs, evidence citations are spot-checked at review, and the decision is the gate before anything reaches a brief or a public page. The question and decision are marked human-led, sources, method and evidence agent-built, and findings the shared output.Pipeline diagram of a competitive teardown in five stages. First, the designer defines the competitor set and the evidence dimensions, tied to a design decision. Second, one agent per competitor captures evidence: onboarding screenshots, pricing pages, verbatim positioning claims, and core flows, into a folder with a dated manifest. Third, findings are normalised against the fixed rubric, with marketing claims cross-checked against the walkthrough and labelled supported, contradicted, or unverified. Fourth, the evidence is synthesised into a comparison matrix, named patterns, and opportunity gaps. Fifth, the designer reviews: sampling cells against evidence, separating observation from inference, and deciding which gaps to pursue. A dashed line returns from review to the competitor set for the quarterly re-run.Pipeline diagram of agentic research synthesis in five stages. Stage one, prepare: the researcher anonymises transcripts, tickets, and reviews, confirms consent, reads three sources, and drafts the codebook. Stage two, code: one agent per source applies the shared codebook, keeping verbatim quotes with participant IDs and line references. Stage three, cluster: an agent merges codes into themes, each with a one-sentence claim, supporting participants, quotes, and a coverage count. Stage four, challenge: a sceptical agent flags thin evidence, non-verbatim quotes, contradictions, and over-generalisation. Stage five, interpret: the researcher spot-checks quotes, decides meaning, sets confidence, parks thin themes, and signs the packet. A green band underneath shows the evidence trail linking every theme back to verbatim quotes, participant IDs, and line references.Loop diagram of quantitative research with agents in six steps. A human frames the question and the decision it informs. The agent helps design the instrument or experiment and critiques it against bias patterns, with sample sizes computed by script. The team collects the data through real survey or experiment tooling and exports it as flat files. The agent runs the analysis with scripts and stated assumptions, including a skeptic pass. The readout passes through a human review gate where numbers are spot-checked and claims compared to the pre-registration, before a human decision. A dashed feedback line shows the decision raising the next question.

Research Packets · concept

Anatomy of a packet

Research Packets · diagram

What each part does downstream

Research Packets · concept

What agents do well: coverage, structure, recall, traceability

Research Packets · checklist

What they do badly: novelty, contact, knowing what is missing

Research Packets · comparison

Source standards: set them before the first packet

Research Packets · concept

Packets as briefing inputs

Audience and outcomes / 04

By the end of this course you can…

UX researchers, product designers who carry research as part of their role, and design leads who need evidence to move faster without becoming shallower.

01

Structure research as packets — question, sources, method, findings, evidence — that agents can build and humans can audit.

02

Run deep desk research and competitive teardowns that cite their sources and separate observation from inference.

03

Synthesise interviews, support tickets, and open-text feedback into themes with traceable evidence.

04

Use agents for survey design, experiment readouts, and funnel diagnosis without laundering weak data into confident claims.

05

Generate journey maps and service blueprints from product data and keep them current.

06

Convert findings into design briefs so research changes what gets built rather than what gets presented.

Who it is for

This is for you if…

  • UX researchers and product designers who carry research in their role
  • Design leads who need evidence without becoming shallower
Who should skip it

This is not for you if…

  • Anyone hoping synthetic users will replace participants
  • Teams that will not keep a human on questions, interpretation, and ethics
Why register now

The practice compounds. Waiting does not.

01

Agents already accelerate screening and synthesis; the risk is shallow confidence.

02

Ethics and participant ownership do not disappear when the desk work gets faster.

03

Research that never becomes a brief is theatre — this course closes that gap.

Price and checkout

Pay once. Keep the course, with updates.

Prefer the full designer catalogue, or designer plus leadership? Upsell paths use the same checkout you already trust.

Pay once. Yours to keep, with updates.

US$39One-time purchase

Buy courseDesigner TrackEverything bundle

Buying for a team? Team seats

FAQ

Before you register

Do you teach synthetic users as a substitute for participants?

No. Agents can speed desk work and structuring. Participants, interpretation, and ethics stay with the researcher. Synthetic users are never treated as a substitute.

Is this a subscription?

Pay once. Yours to keep, with updates. There is no renewing membership for new purchases.

What do updates cover?

All edits and new lessons in an owned course, for the life of the course. Bundles include new courses added to that track for 12 months.

What if a course is retired?

Course retirement gives access to its replacement.

Related material / 05

The sources behind this course.

The course teaches the practice; the books and articles carry the depth, sources, and worked runs it draws on.

The Agentic Designer

The operating model for product designers, design leads, and builders who need to understand what changes when agents join design work.

Leading a Design Organization with Agents

The three leadership courses are sold together for US$300. Designer courses and bundles don't include them, except the Everything bundle, which does. This purchase doesn't open the designer courses.

View course

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, and plan-mode guidance for Claude Code, Codex CLI, OpenCode, and Antigravity CLI.

Read article

Research Packets for Agentic Design

A practical editorial system for turning tool changes, reader questions, screenshots, examples, and experiments into durable agentic-design curriculum.

Read article

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.

Read article