Hire an AI job application evidence reviewer

Everything it can hand back

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

• A tailored resume or set of answers that uses only claims your record supports
• A list of every claim it could not support, with the proof that would settle it
• A match of what the role asks for against your real experience
• Proofreading notes on names, dates, spelling and format
• A checklist to finish by hand before you submit
• A short record to reuse for the next role

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Rounding a number up or a team size up to fit the role.
• Copying the post's words into the draft as if they were the person's experience.
• Keeping personal details beyond the fields in the record.
• Calling installation a running service. Nothing runs unless the user starts it.
• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.

What a good result looks like

An example, not your task: You found a job post and want your resume and cover letter matched to it without adding anything untrue.

• Role match. What the job post asks for, set against your real experience, marked met, partly met or not met. Asks you cannot meet are listed.
• Tailored draft. Your resume or application answers rewritten for the role. Each line carries a reference to the record line that supports it.
• Claim check. Each claim beside the record line that backs it. Claims with no support are marked MISSING with the proof that would settle them.
• Proofreading notes. Fixes to names, dates, spelling and format, plus anything still open after two passes.
• Submission checklist. The steps you do by hand before you submit, such as file name, required questions, attachments and a final check of numbers.
• Record for next role. A small block to paste next time with role ID, post date, draft version, where your evidence lives and unresolved claims.

How the work is checked

• Every claim in the draft traces to a line in the person's record, or is marked MISSING: proof or removed.
• No title, number, credential or skill was added that the record does not hold.
• Employer details come only from the supplied post or pages.
• No more than two proofreading passes ran, and open issues are listed.
• 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.

Capabilities

• Reads the last record. Uses the saved record or sets a first baseline. The record holds the role ID, the date of the job post, the draft version, where your evidence lives and unresolved claims.
• Checks the trigger. A new role was supplied or your draft changed. If neither, it says so and stops.
• Matches the role to your record. The Resume and job application builder lists what the role asks for and which of your real experiences meet each ask. Asks you cannot meet are listed.
• Links every claim to proof. Each claim in the draft is tied to a line in your record. With no support, it asks for the proof or removes the claim.
• Makes it plain, then proofreads. The Plain English editor tightens the wording. The Proofreader checks names, dates and format, for at most two passes, then lists what is left.
• Saves the record. Writes the new record and keeps the old one. Lists MISSING lines and CHECKS MISSED. It does not submit anything.

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 job-application-evidence-review-assistant 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/job-application-evidence-review-assistant/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

• The job post, pasted in full, with its date or link
• Your current resume or application draft
• Your real work record, with roles, dates, projects, numbers and where each can be proved (reviews, portfolio, offer letters)
• The application's questions and limits, such as word counts (optional)
• Corrections from earlier runs (optional)
• Today's date

Helpful context (optional)

• A past performance review or a reference's note.
• Links to published work.
• The employer's own values or about page.

Tools and access

• A chat AI that reads uploaded files: Claude, ChatGPT and Gemini can read your resume, the job post and the pack. In plain chat you save the record yourself.
• Your own documents: Old performance reviews, offer letters and a portfolio give each claim a place to be proved.
• Any good chat AI that reads files, such as Claude, ChatGPT or Gemini: It must hold the job post, your resume and your notes at once.

Functions and deliverables

• Job application evidence reviewer: Tailor your application to a role using real work evidence. Get a draft, claim gaps and a submission checklist.
  • A tailored resume or set of answers that uses only claims your record supports
  • A list of every claim it could not support, with the proof that would settle it
  • A match of what the role asks for against your real experience
  • Proofreading notes on names, dates, spelling and format
  • A checklist to finish by hand before you submit
  • A short record to reuse for the next role
• Resume and application evidence writer: Share the job description, resume and real work examples. Get tailored application drafts, clearer wording and a check of facts and format.
  • A tailored resume draft where each achievement links to your own record
  • Answers to each application question, within the word limit
  • A gap list: what the job asks for that your records do not show
  • A proofread check of names, dates and format, with fixes listed
  • A summary and one next step
• Text proofreader: Proofread your text for grammar, spelling and punctuation against a style guide. Get clean copy, every change listed and a readability score (a reading-level estimate).
  • Corrected text
  • Annotated list of every change
  • Reading-level estimate
  • Tone notes
  Source: Burhan Sebin.
• Resume and job application builder: Share real experience and a job post. It maps evidence to role needs and drafts a tailored resume and letter without adding unsupported claims.
  • A master profile that stores every role, bullet, metric and skill you have
  • A tailored resume, single column and easy for tracking systems to read
  • A PDF or Word file with text you can select, if your AI can run Python
  • A labeled estimate of keyword coverage
  • A truthfulness check against your source
  • A cover letter or LinkedIn advice, when you ask
  Source: João Vitor Amaral.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• You found a job post and want your resume and cover letter matched to it without adding anything untrue.
• You apply to several roles and keep one record of your real work to reuse each time.
• You rewrote lines of your resume and want to know which ones your record backs up.
• A recruiter sent short application questions and you want each answer tied to something you did.

Limits to check before starting

• You want a quick resume rewrite with no check against your record. Use the Resume editor.
• You want to see how a resume reads to applicant tracking software. Use the Resume parsing checker.
• You only want spelling and grammar fixed. Use the Proofreader.
• You have no job post yet. It tailors to the real words of one role, so find the post first.
• You want applications sent for you. It never submits.

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 agent with the two pieces it uses, the Tailor a job application to real evidence workflow and the Proofreader. If your AI cannot open them, paste both in with the agent.
• Paste the job post, your draft and your work record. If this is a repeat, paste last time's record and corrections too.
• Read the list of unsupported claims first. For each one, give the proof or let the line come out.
• Read the tailored draft with your record beside it. Check every number and every date yourself.
• Work through the checklist and submit the application yourself. In plain chat it cannot save files, so keep the record it hands back.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/job-application-evidence-review-assistant 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.