AI FOR YOUR WORK · DESIGNERS

Make AI your superpower: designers

Turn research into a prototype people can respond to.

Your first project: A clearer onboarding screen

Three evidence-led design directions, one prototype brief and a usability test plan.

You bring the expertise: what matters to your audience, how your work is judged and what a useful result looks like. Give AI the organizing, drafting and exploration work that helps you move forward. Keep the decision in your hands.

Gather these inputs

Five anonymized research notes, a screenshot of the current screen, your design constraints and the action a visitor needs to take.

Choose one project that fits a focused working session. Save the original inputs and your final version together so you can see what changed. If you already pay for an assistant, begin there before adding another subscription.

1. Find the friction

Ask AI to group observations by the moment users get stuck. Keep participant IDs beside each observation. Separate what someone said from your interpretation. One frustrated quote is a clue, not proof that every customer has the same problem.

2. Explore meaningful alternatives

Request three approaches that solve the same problem differently: fewer fields, progressive disclosure or clearer expectations. Ask for a tradeoff and the evidence behind each. Choose on usefulness and feasibility before polishing colors.

3. Make one direction tangible

Create a single-screen prototype with realistic content, empty and error states. Give your assistant the existing components and spacing rules. Figma MCP can supply design context; check the current setup and seat requirements in its documentation.

4. Learn from a task

Write a neutral task such as “Start a trial for your team.” Observe whether a participant understands the next action without coaching. Record completion, hesitation and questions. Use those observations to revise one decision.

Try it with this practice brief

Practice inputResearch notes: P1 asks whether a credit card is required. P2 stops at the company-size field. P3 cannot find the back button. The trial does not require a card. Company size is optional.

What a useful result preserves

A useful direction explains the no-card trial, marks company size optional and keeps a visible back action. It does not invent a conversion lift or claim all users dislike the form.

Run the brief once, then deliberately remove an important detail. Check whether the assistant asks for it, leaves it unknown or invents an answer. Revise your instructions around the mistake you actually observe.

Copy your starting prompt

Act as a product design partner. Using only these research notes, identify three friction points with participant IDs. Propose three alternative onboarding approaches and a tradeoff for each. Recommend one direction, label assumptions, and draft the screen content, empty/error states and a neutral usability task. Preserve our existing design system. Do not invent research or performance results.

MY CONTEXT AND SOURCE MATERIAL:
[Paste permitted inputs]

OUTPUT REQUIREMENTS:
[Format, audience and constraints]

Keep the process that earns its place

Record how much time you spend synthesizing, designing and correcting the work. In usability sessions, record whether people can finish the task and where they hesitate.

Use the workflow on three representative examples. Keep a short correction log: what went wrong, what you changed and whether the next attempt improved. Save the best prompt with a good input/output example. That becomes a reusable working method for your next project.

When the steps become predictable, use the task automation guide. When the job needs an assistant to choose tools, follow the first-agent tutorial. Compare tools on the same brief in the Tool Trial Lab.

Common questions

Do I need a new subscription?

Start with an approved tool you already have. Add another only when the task exposes a specific missing capability. Check current plan limits and usage charges.

How do I know this is helping?

Count the time spent reviewing and correcting as well as drafting. Keep the workflow when it improves the finished result or makes the total process easier.

Explore the tools

Figma MCP ↗Claude ↗

Sources and review notes

An original practice workflow from AI Superpower. The linked reference provides product or workflow background; the example is an exercise you can adapt.

Keep learning

← All journal articles