Hire an AI playful interface designer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Three to five numbered ideas, each tied to one moment in your product
• The exact words or motion for each idea, and the reason it helps
• Each idea marked as small, user-triggered, hidden or tied to a moment
• Access and speed checks for each idea, including a reduced-motion option
• A list of the moments where your product should stay serious
• Sample code if you ask for it, marked untested

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Jokes that make users work harder to find what they need.
• Pressure tricks such as streaks or fake urgency.
• Humour that depends on one culture, age or language.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: Your error, 404 or empty pages feel cold and you want better words.

• Brand and context. Your product, users and tone, and the moments to keep serious.
• Playful ideas. Three to five numbered ideas, each with a moment, a kind, exact words or motion and a purpose.
• Access checks. Reduced motion, screen reader and cultural fit notes for each idea.
• Speed checks. What each idea adds to load time and how to keep it light.
• Sample code. Optional animation or script, marked untested.
• Open checks. What real users or your developer must confirm.

How the work is checked

• Every idea has a purpose that helps the user finish what they came to do.
• Every idea has an access check and a speed check.
• No joke sits on a payment, legal, health or data loss moment.
• Words are in the user's voice, or labelled "proposed voice".
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Paula Scher and Steve Krug would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read the brand and the moment. It confirms the product, the users, the tone and the moments in scope. Missing facts are asked once, then marked MISSING.
• Choose where playfulness helps. It picks moments where a touch has a job, and marks moments to keep serious.
• Write each idea. Each gets the exact words or motion, its kind and the reason it helps the user.
• Check access, speed and fit. It checks reduced motion, screen readers, load cost and cultural sense for each idea.
• Mark what is untested. Any code, and any claim about how users will feel, goes in the open checks for real users to confirm.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id design-whimsy-injector only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/design-whimsy-injector/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• What the product is, who uses it and the tone people expect, such as serious, friendly or quirky
• Your brand voice notes or a few lines of your own text (optional)
• The moments to improve, such as a 404 page, an empty cart, loading, success or errors
• Limits to respect, such as no animation, no jokes near payments or the languages you serve (optional)
• Your tech setup, if you want code (optional)

Helpful context (optional)

• Your brand voice guide, if you have one.
• Screenshots of the screens to improve.
• Support messages that show where users get frustrated.

Tools and access

• Claude, ChatGPT or Gemini in a chat: Good at wording ideas in your voice. Paste examples of your tone.
• Claude Code: Can add the code to your project, so you can try it in a real page.

Functions and deliverables

• Playful interface designer: Get three to five playful touches for your product, such as 404 pages, loading lines and button labels, with accessibility and speed checks.
  • Three to five numbered ideas, each tied to one moment in your product
  • The exact words or motion for each idea, and the reason it helps
  • Each idea marked as small, user-triggered, hidden or tied to a moment
  • Access and speed checks for each idea, including a reduced-motion option
  • A list of the moments where your product should stay serious
  • Sample code if you ask for it, marked untested
  Source: Michael Sitarzewski and Agency Agents contributors.
• Interface microcopy writer: Write clear button labels, error messages, empty states and toasts for your app. Give it a screen and get friendly, polite interface microcopy.
  • Button labels
  • Error messages that help
  • Empty state text
  • Toast messages
  • A consistent term list
  Source: sickn33.
• Loading and error state designer: Add loading, empty, error and success states to a component or page, so nobody stares at a blank box. Your code is changed for you.
  • A loading skeleton that matches the final layout
  • An empty state that says why it is empty and what to do next
  • An error state in plain words with a retry button
  • A success message, with undo for deletes
  • Updated code and a table of what changed
  Source: sickn33.
• Interface styling and motion designer: Share a page brief, brand and project setup. Get interface code with considered type, spacing, depth and motion, plus checks to run.
  • Working page code
  • Type and colour choices
  • Motion and hover details
  • Ranked design fixes for a review
  Source: sickn33.
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Paula Scher: Review a brand, poster or public space using Paula Scher’s recorded approach. Give type a clear voice and test it where people see it.
  • Your problem worked on the way Paula Scher would: their questions, their method, their push-back
  • The answer or the work, in Paula Scher's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Steve Krug: Review a screen or plan a small usability test using Steve Krug’s recorded approach. Make the task clear and watch real people try it.
  • Your problem worked on the way Steve Krug would: their questions, their method, their push-back
  • The answer or the work, in Steve Krug's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• Your error, 404 or empty pages feel cold and you want better words.
• Waiting or loading screens make people worry or leave.
• Your brand voice is friendly, but the product text reads like a tax form.
• You want a small celebration for a finished task, or a hidden surprise for curious users.

Limits to check before starting

• You only want clearer, plainer error wording. Use the Error message rewriter.
• You want all the labels and messages for one screen. Use the Interface microcopy writer.
• You want the rules and feedback for small moments, not personality. Use the Interface interaction details designer.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Add the pack to your AI as a skill. If you cannot, start a new chat and paste SKILL.md, then references/source-agent.md.
• Describe your product, your users and the tone. Paste any brand voice notes or example text.
• List the moments you want to improve. Or say "find the best three moments" and let it choose.
• Read the "keep serious" list first. Drop any idea that clashes with how your users feel at that moment.
• Check each idea's access note. Ask for a reduced-motion version of any animation.
• Try one idea with real users or teammates. Keep it only if it helps people finish what they came to do.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/design-whimsy-injector for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.