Hire an AI hiring interview and candidate comparison planner

Everything it can hand back

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

• An interview plan with stages, owners and what each stage checks
• A scorecard per stage and a work test with a scoring guide
• The candidates compared on evidence, with bias flags, for you to decide
• A reply drafted for every candidate, ready for you to send

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

• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.
• Treating a template as legal advice.

What a good result looks like

An example, not your task: You have four or more candidates for one role and the team disagrees about them.

• Interview plan. Each stage, who runs it, how long it takes and what it checks, so no stage repeats another.
• Scorecards. One per stage, with set questions, strong and weak answer signs and one rating scale.
• Work test. A short task from the real job, with a scoring guide and fairness checks.
• Comparison. Candidates compared on scorecard evidence, with flags on notes that rest on feel or unrelated traits.
• Replies. The offer call for your pick and a clear, kind reply for every other candidate.
• HAND-BACK SUMMARY. Each step's file, any step not run, and every MISSING line in one list.

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.

Capabilities

• Plan the stages. Sets the stages for the role and level, names who runs each and what it checks, so no two stages test the same thing.
• Write the scorecards. Writes one scorecard per stage with set questions, strong and weak answer signs and one rating scale for everyone.
• Design a work test. Builds a short task from the real job with a scoring guide and checks that it is fair to every candidate.
• Run the interviews. A pause. Run the interviews and the work test. Every interviewer fills in their scorecard before they talk to anyone else about a candidate.
• Compare on evidence. Compares candidates on the scorecard evidence only, flags notes that rest on feel or on things unrelated to the job, and leaves the decision to you.
• Draft every reply. Drafts the offer call and a clear, kind message for every other candidate. You read and send them.

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 run-fair-interviews-and-choose-on-evidence 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/run-fair-interviews-and-choose-on-evidence/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 role, its level, what the person must be able to do and the main tasks of their first 90 days
• Who will interview and how much time you have
• After the interviews, every interviewer's scorecard notes
• Interview transcripts or recordings (optional)
• Your hiring decision, once you have read the comparison
• For each reply, the candidate's first name, where they are in the process, the next step and who signs it

Helpful context (optional)

• A real, anonymised task from the last month
• Your company's interview and data rules
• Notes on why past hires for this role worked or did not

Tools and access

• Any good chat AI: Every step is text: plans, scorecards and comparisons.
• A shared document or hiring tool: Holds the scorecards so interviewers fill them in before the debrief.
• Any good chat AI: Claude, ChatGPT or Gemini can all write the task and scoring guide from text. No code or files are needed.
• Any good chat AI: This is a writing job. Claude, ChatGPT or Gemini all do it well, with nothing to install.

Functions and deliverables

• Hiring interview and candidate comparison planner: Share the role, criteria and candidate evidence. Get interview stages, scorecards, a work test, later comparisons and reply drafts.
  • An interview plan with stages, owners and what each stage checks
  • A scorecard per stage and a work test with a scoring guide
  • The candidates compared on evidence, with bias flags, for you to decide
  • A reply drafted for every candidate, ready for you to send
• Interview process planner: Plan your interview process for any role. Give it the role and level. You get each stage, who runs it and what it checks.
  • A stage-by-stage interview plan
  • A skills-to-stage map
  • An owner and length for each stage
  • Advance and reject criteria
  • A candidate timeline
  Source: Carlo Pezzuto.
• Interview scorecard builder: Build an interview scorecard for each hiring stage. Get rating guides, questions with probes and a phone screen script that keep ratings tied to evidence.
  • One scorecard per stage
  • Rating guides with observable behaviours
  • A bank of questions with follow-up probes
  • A phone screen script
  • A debrief checklist
  • A separate gut feeling field
  • Calibration exercises for interviewers
  Source: Carlo Pezzuto.
• Work sample test designer: Design a work sample test for any role, with a scoring guide and fairness checks, so you hire on what candidates can actually do.
  • A test type picked for your role, with the reason
  • A task brief you can send to candidates
  • A scoring guide with examples at each rating
  • A short plan to get your markers scoring alike
  • Bias and fairness checks on the task
  • A way to combine test scores with interview notes
  Source: Tuan Duc Tran.
• Fair candidate comparer: Compare job candidates fairly. Paste interview transcripts and your scorecard. You get scored answers, evidence gaps and bias checks.
  • A scorecard filled in question by question, with quotes
  • A written screen evaluation grouped by skill
  • A side-by-side comparison of candidates with a confidence level
  • A list of evidence gaps, interviewer gaps and bias flags
  Source: Carlo Pezzuto.
• Candidate message drafter: Write the right email to a job candidate at any stage, from screening invite to offer or rejection, with one clear next step and a send time.
  • A subject line and email draft for that stage
  • One clear ask for the candidate
  • A suggested send time
  • A warmer and a more direct wording for the key lines
  • A list of any gaps you still need to fill
  Source: Carlo Pezzuto.
• 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 have four or more candidates for one role and the team disagrees about them.
• Your last hire interviewed well and struggled in the job.
• You want a process you can show a candidate who asks how the decision was made.

Limits to check before starting

• You have one candidate or fewer than four: use a plain scorecard of your own and a simple chat with your team.
• You only need the job post and the offer letter: use the Hiring document and candidate reviewer workflow.
• You need to check a candidate's background or references: ask the candidate for referees and call them yourself.

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 pack. It holds HANDOFF.md and five skill files, in the order they run: Interview process planner, Interview scorecard builder, Work sample test designer, Fair candidate comparer, then Candidate message drafter.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the role and what it needs. It plans the stages, the scorecards and the work test.
• Run the interviews. Each interviewer fills in their scorecard before anyone discusses a candidate.
• Paste the scorecards back. It compares the candidates and drafts the replies. You decide, then send.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/run-fair-interviews-and-choose-on-evidence 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.