Classic methods
Moderated sessions, interviews, card sorting, paper prototypes.
Proven. Needs people and time.
Øredev 2026
Dora MakszyHead of Design
Use ↓ Space to move forward, ↑ to go back, F for full screen
The problem · summer 2025
We could not afford to guess. But we also could not afford to wait.
Theory & methods
The Double Diamond is a visual representation of the design and innovation process.

Illustration by Sid Saladi
Theory & methods
Before you build, make sure it solves the right problem in the right way. UX research helps you evaluate and validate before you decide.
Click the card to compare.
Theory & methods
Theory & methods
Building the tool
Not everything worked on the first try.
Building the tool
A structured command for the AI tool is basically a good definition of what you want to build and why.
Building the tool
Building the tool
Running the research: trusting the participants.
Value
Module,Tasks,Total time,Success rate,Clicks/Actions,Avg Task Time Search,4,35s,100%,25,9s Navigation,2,221s,100%,136,111s Versioning,3,56s,100%,6 / 6,19s NAVIGATION CARD SORTING RESULTS Category,Items Count,Is Custom,Items Inbound,2,No,Goods receiving; Incoming returns overview Outbound,4,No,Advance shipping notice; Order batching; Review order status; Reprinting Inventory,2,No,Inspection; Compression Control Room,13,No,Review inbound order status; Review outbound order status; Picking strategies; Conveyor status; Review process engine status; Robotic piece picking console; PLC Alerts; Set robot arm in maintenance mode; Staff planning; Shift planning; Alarm center; Review stock deviations; Review material master data Configuration,12,No,AutoStore grid configuration; Conveyor configuration; Configure picking workflow; Configure putaway workflow; Review external communications; Notification chain configuration; Change language settings; Define base units for length; Edit user privileges; Edit user roles; Add printing service; Add shipping service Insights,1,No,Robotic piece picking insight Settings,4,Yes,Software version; Get help; Create service ticket; Schedule software upgrade Logs,6,Yes,Order logs; Stock ledger; Audit trail; Event log; Printing log; Notification log
Value
Value
One year later
In 2025, AI helped me build a test. In 2026, AI sits inside the test, and the researcher still sets the bar.
Figma Make builds a mock test tool. AI generates the prototype.
The findings turned into actionable steps. Since then the company has moved fully to smart use of AI, so the tool had to grow too.
Built with Claude, inside the real product. AI recommends, checks and drafts. The researcher decides.
One year later
| v1 · Figma Make, 2025 | v2 · Claude, 2026 | |
|---|---|---|
| What to test | I decided alone | Claude recommends, I decide |
| Pass / fail bar | Set by hand, slow to define objectively | Claude proposes targets per metric, I confirm them |
| Test screensNew | Mock screens I drew by hand | The real product, from my repository |
| TasksNew | Invented to fit the mock | Built from the hypotheses and what the product can really do |
| Task wording | Checked by me | Bias check flags leading task briefs |
| Analysis | Manual, from CSV | Measured against the targets, plus an AI draft |
| Keeping it currentNew | Rebuild when the product changes | Evolves with the code in the same repository |
| Build time | About a month | Hours to days |
One year later · Claude Code
Claude builds the test into my own repository, so participants test the real thing, not a mock I drew.
One year later · Test Suite 2.0
Here are three scenarios for H1, using what Site Designer can do today:
A preference question alone will not tell you whether people can find their way. Pair it with a task.
One year later · Test Suite 2.0
I suggest these metrics. Pick the ones that fit:
Done. Success ≥ 90% set by you and SEQ ≥ 5.5 AI suggested. I will not change your value.
One year later · Test Suite 2.0
When tasks are written against the real product, menu names leak into the brief easily. Claude flags it.
Task briefSite Designer: a conveyor layout with a PLC and a merge
One year later · Test Suite 2.0
Nothing new in UX research: we always measured against a bar set in advance. Now that structure is faster to set up.
Example numbers, for illustration.
One year later · Usability Lab
One task, three questions, then straight to the export.
Choosing how to test
Classic methods still work. The AI-built tool gets its discipline from them; it does not replace them.
Moderated sessions, interviews, card sorting, paper prototypes.
Proven. Needs people and time.
Built and adapted with Claude, runs async on the real product.
Fast. Depends on an AI provider.
An open model on your own machines, or no AI at all.
Predictable. Data stays in-house.
Choosing how to test
It makes us faster. It also makes us depend on things we do not control.
One year later
Most of the 2025 failures are still true. These three are new.
Value
Best practices
Build your own!
