Page 142 · Module 06, Build Your Team · this screen continues that page

All 108 frameworks
6.4IntermediateModule 06 · Build Your Team

Hiring with AI -Talent Filter

Build the interview system that hire stheright person, not the best interviewer

The prompt

Copy & paste ready
6.4Hiring with AI -Talent Filter
Act as a structured hiring consultant. Role I am hiring for : [JOB TITLE AND KEY RESPONSIBILITIES] Team context : [STAGE, CULTURE, WHO THEY WILL WORK WITH] Non-negotiables : [MUST-HAVE SKILLS OR EXPERIENCE] Step 1 : Define the top 4 success criteria for this role what does excellent performance look like in year one? Step 2 : For each criterion, write 2 STAR-format behavioural interview questions. (Tell me about a time when...) Step 3 : For each question, define what a strong answer looks like vs a weak answer 2 lines each. Step 4 : Write one work sample task I could give candidates to test the most critical skill directly. Step 5 : Write 3 red-flag signals to watch for in interviews. Talent Filter Hiring Process Define Success Criteria Consistent Scoring Rubric Establish 3-5 key criteria for Use a rubric for fair and success consistent scoring Behavioral Questions AI-Assisted Analysis Ask STAR format questions Analyze candidate data with for each criterion AI tools
LabelsReplace theseSwap the role below

LabelsReplace theseSwap the role below

Pro tip, from the book

The work sample task (Step 4) is the single highest-signal hiring tool available. A 2-hour task relevant to the actual job outpredicts any amount of interviewing. Candidates who decline the task often self-select out for good reason. Candidates who complete it brilliantly and explain their thinking are almost always the right hire.

Who should run this prompt

Module role profile

Who should advise on people and leadership decisions? Leadership decisions are the highest-leverage decisions in any organisation — and the hardest to get right because the stakes are human. The roles on this page bring the perspectives of people who have seen hundreds of teams succeed and fail. Use them before hiring, before giving difficult feedback, before restructuring, and before having the conversations you have been avoiding.

Choose any role to drop it into the prompt above. Only the highlighted opening clause changes — the rest of the prompt stays exactly as printed.

Internal rolesThink from inside the organisation
Outside perspectivesChallenge your blind spots

◆◆◆◆◆ → ◆ seniority, board level down to specialist outside the organisation

How to make any role sharper

  1. Add years of experience: "...with 15 years in enterprise SaaS" produces different depth than just the title.
  2. Add what they care most about: "You care most about [X]" shapes every word of the output.
  3. Add their communication style: "Be direct. Flag risks first. No jargon." changes the tone entirely.
See also: 1.3 Role Prompting - The Expert Chair

Use this when

The problem it solves

You've made a hire that looked great on paper and in interviews, then didn't work out. Your hiring process relies too much on gut feel. Interviews feel like conversations but don't consistently predict performance.

How the framework works

From the printed page

Structured interviewing asking all candidates the same pre-defined questions scored against consistent criteria has been shown in multiple studies to significantly outperform unstructured interviews in predicting job performance. The Talent Filter approach adds a layer: define the role's top 3–5 success criteria before writing a job description, build behavioural questions for each criterion (STAR format: Situation, Task, Action, Result), score each answer against a rubric, and use AI to help build both the questions and the scoring guide. The goal is to reduce bias and increase the signal-to-noise ratio of every interview.

The method, in four moves

Do these in order
1

Define the 3–5 success criteria for the role before writing the job description.

2

Write at least 2 STAR-format behavioural questions per criterion.

3

Score every candidate on the same rubric not your overall impression.

4

Use the prompt below to generate role-specific questions and scoring guides instantly. "They didn't feel like a fit" is not a score, it's the bias you built this framework to remove sneaking back in through the back door. If the rubric can't explain the rejection, the rubric didn't make the decision. Structure Doesn't Kill the Feel

Where the framework comes from

Structured interviewing research — Schmidt & Hunter, Journal of Applied Psychology, 1998

When this page changes, your copy of the book does not have to.

The book prints the framework. This page keeps it — and keeps the prompt current, because prompting technique moves faster than print does. When it moves, this page is rewritten and the code in your copy keeps pointing at it. No second edition, no replacement purchase, no account.

If something here looks wrong — a prompt that does not match its framework, a figure that reads oddly — tell Raphy. That correction reaches every printed copy at once.

Framework6.4 of 108
Printed onPages 141142
Prompt extracted18 Sept 2026
Costs to readNothing, no account

Copying is free. An account keeps them.

Nothing on this page is behind a login and nothing ever will be. Save any prompt to your own list, pick up on another device, and send a colleague a link with your name on it. No card, no trial, no paywall on the prompts themselves.

See how it works
Save this framework to your own list
Pick up where you left off on another device
Send a colleague a link with your name on it