Hire an AI translated interface reviewer

Everything it can hand back

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

• A string-by-string table with meaning, term, placeholder and plural problems
• Revised wording for each string that failed
• Unclear original labels, with clearer wording that keeps meaning and variables
• A layout checklist of screens and states where longer text may break
• A list of what could not be checked, such as a language your AI cannot judge well

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

• Inventing strings, translations, screens or test results.
• Changing a placeholder or removing a variable to make a sentence read better.
• Saying a layout fits when you had no screenshot to check.
• Treating a guess about a language you cannot judge as a check.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.

What a good result looks like

An example, not your task: A translation vendor sends back your strings file and you want a second check before release.

• Meaning check. A table of each string with its meaning, term, placeholder and plural problems.
• Revised wording. A fixed translation for each string that failed, with the reason for the change.
• Source fixes. Unclear original labels with clearer wording that keeps their meaning and variables.
• Layout checklist. Screens and states where longer, cut off or reversed text may break, and what to look at.
• Hand-back summary. Files saved, MISSING lines, checks not run, languages needing a fluent reader, and one next step.

How the work is checked

• Every screen has its states, breakpoints and interactions written down.
• Colour pairs and type sizes pass the stated contrast checks.
• The handoff names components, tokens and open questions.
• 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 Steve Krug and David Carson would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plain words interface rewriter. Reads the original strings and marks unclear labels. Suggests clearer wording that keeps the meaning and every variable. Hands step 2 the original strings and a list of source fixes. Check before moving on, no variable such as {name} was changed or dropped.
• Translator. Compares each translated string with the original for meaning, set terms, placeholders and plural forms. Marks languages it cannot judge well. Hands step 3 the table of strings and their problems. Check before moving on, every string ID appears once.
• Screen states designer. Lists the screens and states each string appears in, such as empty, loading and error. Marks where translated text is longer, cut off or reads in another direction. Hands back the layout checklist. Check before moving on, any state with no translated text is listed as missing.

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 check-a-translated-interface-still-makes-sense 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/check-a-translated-interface-still-makes-sense/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

• Your original interface text, as a strings file, a spreadsheet or pasted lines, with an ID for each string if you have one
• The translated text for the same strings
• The target language and region, such as French (Canada)
• Screenshots, or a list of the screens each string appears on (optional)
• Your list of terms that must always be translated the same way (optional)

Helpful context (optional)

• Approved examples of a good result.
• A named reviewer and their acceptance rules.

Tools and access

• A capable chat AI with file support: Read the full pack and supplied sources; connected actions need the corresponding authorized tools.
• Any good chat AI: Rewriting text in a given set of words is work any strong chat AI does well.
• A person who has never used it: A new hire shows which words still confuse. No tool replaces that test.

Functions and deliverables

• Translated interface reviewer: Compare original and translated screen text. Check meaning, variables and missing states, then flag layouts that need a visual review.
  • A string-by-string table with meaning, term, placeholder and plural problems
  • Revised wording for each string that failed
  • Unclear original labels, with clearer wording that keeps meaning and variables
  • A layout checklist of screens and states where longer text may break
  • A list of what could not be checked, such as a language your AI cannot judge well
• Forms and instructions rewriter: Share forms, screen text or steps and your users’ words. Get a plain rewrite, a swap table and open questions.
  • A rewrite in the words your users say
  • A list of old terms and their replacements
  • Instructions that start with a verb
  • A read-aloud check and the questions a new hire would still ask
• Text translator: Translate text into another language so it reads like a local wrote it. Keeps your terms, tone and formatting the same throughout.
  • A natural translation
  • Formatting and placeholders kept intact
  • Local units and dates
  • Translator notes on tricky choices
  Source: Burhan Sebin.
• Screen states designer: Find the empty, loading, error and offline states your screen is missing, then build each one. Use it as a screen states checklist and builder.
  • A list of states that can happen on that screen
  • Copy and layout for each state
  • Error messages with a clear next step
  • Built versions in your code
  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
• 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
• David Carson: Review a layout or stale template using David Carson’s recorded approach. Start with the audience and message, then test whether the experiment communicates.
  • Your problem worked on the way David Carson would: their questions, their method, their push-back
  • The answer or the work, in David Carson'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

• A translation vendor sends back your strings file and you want a second check before release.
• Your German or Spanish app shows cut-off buttons, or users say a label means something else.
• You are adding a new language and want to test the first screens before the rest.
• A support ticket says the translated checkout makes no sense and you need to find the strings behind it.

Limits to check before starting

• You have one string or a short text to translate. Use the Translator.
• You want a whole article or help page translated. Use the Article translator.
• Your app still has text typed into the code and no translation setup. Use the App translation setup helper first.
• The text is legal, medical or safety wording. A qualified human reviewer must sign it off.

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 workflow pack and add it to your AI, such as Claude, ChatGPT or Gemini. One that reads files works best.
• Paste or attach the original strings and the translated strings. Say the target language and region once at the top.
• Add screenshots or a screen list if you have them. Without them, the layout results are warnings, not checks.
• After step 2, read the table. Fix every row marked meaning changed or placeholder missing before anything else.
• Ask a fluent reader to check any language the summary lists as not assessed. Then look at the flagged layouts in your running app.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-a-translated-interface-still-makes-sense 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.