← John Etokhana

How I design with AI

First published July 2026 · Ongoing

I use AI, mostly Claude and Claude Code, across most of what I do as a designer. Not as a novelty, and not to make prettier pictures faster. I use it to remove the cost of the parts that were never the point, so I can spend more time on the part that is: deciding what to build, and knowing when something is off even though it technically works. Here is what that looks like in practice.

1I prototype in the real stack

The best way to know if a flow works is to use it, not to look at it. On Episode I built the harder flows in code: the generation loader, the brand-confirm step, the Studio shell. When the prototype is the real React app, timing, empty states and error paths get designed against real data instead of faked in a static file and lost in handoff.

Claude Code makes that cheap enough to do early, so I can put something real in front of a teammate or a user before the idea has hardened. Most of it gets thrown away. That is the point.

Below is Yada, a Bible reader I'm building. Claude Code works through the build plan while the app runs in the simulator beside it, and I check each screen against the design.

Build the next release from the build plan.
Thinking…
The End page settles correctly, but two things differ from the design: the passage bar still shows, and the header is gone. Fixing both.
↳Ran 2 commands✓
Typecheck is clean. Next: licensed versions, search, bookmarks and compare. Reading those frames.
↳Re-render frames✓
Adding an 8-second limit on licensed loads, so a slow load becomes a sentence rather than a blank page.
Yada reading John 1, with Understand 1:1 to 18 and Listen in the bar

Tap a verse, or Listen.

2I make the call, then update Figma

Judgment is still the job. AI is good at laying the options out and arguing both sides. It is not the one who decides. A typical loop: Claude reads the Jira ticket and inspects the Figma frame, tells me exactly what is off, and lays out the change. I make the call, and it carries the decision into the file.

Designing with Claude
Recommend changes for the spacing issue in PROJ-1842. Figma: figma.com/design/…
Thinking…
↳get_issue· Jira✓
PROJ-1842: Card spacing inconsistent with design
↳get_design_context· Figma✓
Frame: Settings/Card — padding 24, gap 12
The card padding should be 24 not 16, and the item gap 12 not 8. I'd also change the subtitle from "Manage your settings" to "Workspace settings" to match the nav.
PropertyCurrentRecommended
Card padding16px24px
Item gap8px12px
SubtitleManage your settingsWorkspace settings

3Research at the speed of the question

The slow part of research was never the interview. It was turning forty transcripts and a survey export into something you can act on before the moment passes. I point Claude at the raw material and my questions, and it helps me find the pattern, which I then verify against the data myself.

On Rivva this is how I pressure-tested the number the whole team trusted. I asked whether the event we called activation actually predicted whether anyone stayed. It barely did: it fired on setup, before a user had scheduled or finished any real work. Cohorting on behaviour instead surfaced a much stronger correlation, which I then verified in the data myself. The synthesis was fast. The judgment about what to do with it, redefining activation around experienced value, was the work.

Activation analysis
Does our activation event predict whether someone stays? Cohort the last 8 weeks.
Thinking…
↳query· Analytics✓
Weekly cohorts · activation vs retained
Barely. The event fires on setup, before any real work. Cohorting on behaviour instead:
MeasureResult
Activation as finished setup56.8% → 50.2% while users grew
3 tasks scheduled by Nia, 1 completed, in 48hFar more likely to return
Cohort sizeAbout 100 people a week

4First drafts, never blank

A blank page costs more than it should. PRDs, research briefs, test scripts, screeners: all of them take real time to draft from nothing, and none of them are better for having been started from scratch. I hand Claude the product brief and a template, and it fills in the structure. Then I review, cut and sharpen.

Research brief · draft
Draft the research brief for the onboarding v2 test. Use our template.
Thinking…
↳read_file· brief-template.md✓
Loaded: objectives · hypotheses · tasks · screener
Filled in the structure from the product brief. Review and sharpen.
Objective
Can a new user reach a first plan without help?
Hypothesis
Speaking one task is faster than filling in a profile.
Tasks
1. Set up the app from the store link. 2. Add what's on your plate today.

5Checking my work for accessibility

AI is good at the checks people skip. I ask Claude to go through what I've built for keyboard focus, what a screen reader hears, and contrast. Then I check each finding live before anything changes.

Two fixes from Episode in September. Keyboard focus rings never drew: a pair of styles cancelled each other out, so 117 controls across 83 files showed no focus at all. And the whole chat was a live region, so a screen reader read out every word as it streamed. Now it says "Reply ready" once, when the reply is finished.

Check the chat for keyboard and screen reader problems. Verify anything you find in the browser.
Thinking…
↳inspect· a :focus-visible button✓
outline-style: none
Two real problems. Both are verified live.
ProblemFix
No focus ring on 117 controlsDrop the style that cancels the outline
Screen readers read every streamed wordAnnounce "Reply ready" once

6Designing the AI, not just using it

Using AI to work is half of it. The other half is designing the AI that ships to users, and there the hard part is restraint. On Rivva I designed Nia as a controlled action layer: it could break a vague task into steps, replan a day, draft a message or suggest the next move, but nothing was scheduled, sent or committed until the user said so.

The same rule runs through Episode's automation, which shows what it is doing and hands control back on demand. When the machine can act, the design job is deciding what it may do on its own, and making the moment of control impossible to miss.

Rivva · Nia
My day fell apart. Can you fix it?
Here's a lighter plan. I moved your deep work to your morning peak and dropped a low-priority item. Nothing is saved yet.
2 changes to review
Revamp brand guidelines
Moved to 09:00, your morning peak
Newsletter draft
Dropped for today, low priority
CancelConfirm
Ask Nia…↑

7How I keep AI from shipping slop

AI is quick to make something that works and is slightly wrong, so I never ask it for finished work. I give it real context first: screens from apps that solve the same problem, and the design tokens it is allowed to use. Then I ask for a few directions, pick one, and sculpt it in small passes, one change at a time, saving after each so any pass can be undone.

Before anything goes up for review, I run a cleanup pass for what AI tends to add: comments that narrate the code, checks for things that cannot happen, colours that are not in the system. And a check in the code fails on any colour or text size outside the design system, so drift is caught before a person has to spot it.

The part that does not get cheaper

AI removed the cost of execution across all of this. It did not remove the need for taste. Knowing what to build, what to leave out, and when something feels wrong even though it works: that instinct still has to be earned the slow way, by shipping things and watching people use them. The tool gives me more reps at the decisions that matter, and fewer at the ones that never did.

What I reach for
Design & thinkingClaude·Hex·Magic Patterns·Figma·Mobbin
BuildClaude Code·Cursor·React & TypeScript
Working with peopleLoom·Slack·Monologue
© 2026 John Etokhana ← All work

On repeat

ForgivenessAsake
↑↓ to move ↵ to openLondon