Hire an AI logo design planner and reviewer

Everything it can hand back

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

• A brief with core facts, the one idea the work must carry, three to five limits and what is left free
• A mark plan with the answer already in the brief, the obvious options tried and one surprising move
• A list of ideas to sketch on paper before you open any software
• A score out of 100 for each finished option, with the seven tests and the one-colour and small-size check
• A keep, fix or drop call with one reason, and for a redesign a note on whether the fault is real

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

• 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: You need a logo or mark and want a clear brief to hand a designer or an AI tool.

• Design brief. Core facts, the one idea the work must carry, three to five limits, and what is left free.
• Brand mark plan. The answer already in the brief, the obvious options tried, one surprising move, and ideas to sketch first.
• Logo strength test. Each finished option scored out of 100 on seven tests, plus a one-colour and small-size check.
• Keep, fix or drop call. A clear call for each option with one reason, and for a redesign a note on whether the fault is real.
• Hand-back summary. Each step's file, and every missing item listed in one place.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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 Paul Rand and Milton Glaser would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Writes the brief. Pulls out the core facts, picks the one idea the work must carry and sets three to five limits, with what is left free.
• Plans the mark. Reads the brief for the answer already in it, tries the obvious options and adds one surprising move on top of what people already know.
• Sets the tests. Plans how to test the mark at the smallest and largest use, and lists ideas to sketch on paper first.
• Waits for your sketches. You sketch, pick and finish a few options. Nothing more runs until you bring them back.
• Tests each idea. Scores each finished option on seven tests, in one colour and at a very small size, against the brief and the mark plan.
• Makes the call. Gives a score out of 100, a keep, fix or drop call and one reason for each option.

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 brand-mark-design 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/brand-mark-design/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

• A few lines on the job, such as what it is for, when and where
• Who it is for, and what they should do or see differently
• Limits you already know, such as budget or size (optional)
• Your brand file (optional)
• Notes from a call or visit with the client, and marks you admire or want to avoid (optional)
• A day or more to sketch the ideas and finish a few options
• Your finished options, as images, and the smallest size the mark will be used

Tools and access

• Any good chat AI: Shaping a loose job into a brief is text work any strong chat AI does well.
• A shared folder or board: The collecting step needs a place where ten images can sit side by side.
• Any good chat AI: Reading a brief and planning a mark is text work any strong chat AI does well.
• Paper and a marker: The plan starts with paper sketches. Software comes after.
• A tool to view the mark at tiny and huge sizes: Any design tool or even a phone camera, to test the sketches at thumbnail size and at wall size.
• Any good chat AI that reads images: It needs to look at the logo images.
• A design tool: Use it to shrink and desaturate each idea for the small-size check.

Functions and deliverables

• Logo design planner and reviewer: Create a logo brief and mark plan, then review finished design options against seven tests.
  • A brief with core facts, the one idea the work must carry, three to five limits and what is left free
  • A mark plan with the answer already in the brief, the obvious options tried and one surprising move
  • A list of ideas to sketch on paper before you open any software
  • A score out of 100 for each finished option, with the seven tests and the one-colour and small-size check
  • A keep, fix or drop call with one reason, and for a redesign a note on whether the fault is real
• Design brief rules writer: Turn a loose design job into a design brief with three to five firm limits and room to play. Give it the job and the audience.
  • Core facts: what, why, when and where
  • The one idea the work must carry, in a sentence
  • Three to five firm limits and what is left free
  • A collecting step and a plain statement of the need
• Brand logo planner: Share a brief and existing brand rules. Get logo concepts, size checks, a sketch plan and a short design direction.
  • The answer already in the brief
  • Obvious options tried, with the ones that work
  • One surprising move on top of what people know
  • A mark plan: tests, frame rules and a list of ideas to sketch
• Logo strength tester: Test your logo ideas before you pick one. Get each scored out of 100 on seven tests, plus a one-colour and small-size check, with a keep, fix or drop call.
  • A score out of 100 for each idea, with the working
  • Seven test results plus the one-colour and small-size check
  • A keep, fix or drop call with one reason
  • For a redesign, a plain note on who wants the change and whether the fault is real
• 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
• Paul Rand: Review a logo, identity or layout using Paul Rand’s recorded approach. Find one clear idea, simplify the form and check practical use.
  • Your problem worked on the way Paul Rand would: their questions, their method, their push-back
  • The answer or the work, in Paul Rand's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Milton Glaser: Review a design message using Milton Glaser’s recorded approach. Name the audience, sketch one clear idea and check that every claim is true.
  • Your problem worked on the way Milton Glaser would: their questions, their method, their push-back
  • The answer or the work, in Milton Glaser'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

• You need a logo or mark and want a clear brief to hand a designer or an AI tool.
• You have three logo ideas and can't tell which one is best without a fight.
• You are thinking of redesigning your mark and want to know if the fault is real or only a wish for change.

Limits to check before starting

• You need a full brand identity with colours, fonts and voice: use the Visual system rules writer, or hire a designer with the brief this makes.
• Your logo is already in production: ask your designer to check the files instead, since this works best before sketching.
• You only want a wordmark, a logo made from the brand name in type: use the Wordmark sketch planner.

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.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Describe the job. It writes the brief and the mark plan, then stops.
• Sketch the ideas on paper and make a few finished options. Attach the images, tell it the smallest size, and say "carry on".

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/brand-mark-design 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.