Home · Business · HR & People · Job ads & screening

YES

As of 13 August 2026, AI can create a pre-screening questionnaire for applicants.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ita colleague

What the alternative costsManatal is a purpose-built AI recruitment platform that supports candidate scoring, enrichment and pipeline automation.

If this goes wrong: unsuitable or discriminatory questions can exclude capable applicants and expose your organisation to complaints or legal costs.

What to actually do

  1. Hand it to a person

    The route this page recommends

    A person who owns the outcome does this end to end, worth it when the failure is dear.

  2. Use a tool built for this

    Second choice

  3. Do it yourself

    The distant third

    A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open the current job description and copy the role title, duties, essential criteria, desirable criteria, location and working arrangements into a separate document.
    2. Remove criteria that are preferences rather than genuine requirements, and ask the hiring manager to confirm the final essential criteria before drafting.
    3. Open a chatbot and paste the prompt with the confirmed role information, leaving out applicant names, contact details and other unnecessary personal data.
    4. Ask the chatbot to produce the questionnaire, response types, objective scoring guide and flagged questions in separate sections.
    5. Compare every drafted question with the approved essential criteria and delete questions that do not test a real requirement or that ask for unnecessary personal information.
    6. Ask the hiring manager or HR colleague to check the final questions, scoring guide, reasonable-adjustment route and data-collection purpose before putting the questionnaire on the application platform.

    Prompt

    Create a pre-screening questionnaire for applicants to the role below. Use UK English. Ask only questions that are directly relevant to the stated selection criteria, and do not ask about protected characteristics, health, family circumstances, age, religion, nationality, or other personal matters unless a lawful and clearly relevant exception is supplied. Separate essential screening questions from optional questions. For each question, state the response type, such as yes or no, multiple choice, short answer, or eligibility confirmation. Include an objective scoring guide based only on the essential criteria. Do not make hiring decisions, infer protected characteristics, or invent role requirements. Flag any question that needs review by the hiring manager or an HR or employment-law specialist. Keep the questionnaire concise and suitable for an online application form.

Role title: [ROLE TITLE]
Job description: [PASTE JOB DESCRIPTION]
Essential criteria: [PASTE ESSENTIAL CRITERIA]
Desirable criteria: [PASTE DESIRABLE CRITERIA]
Working arrangements and location: [PASTE DETAILS]
Eligibility or practical requirements that genuinely apply: [PASTE DETAILS]
Application platform or response limits: [PASTE DETAILS]

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

  • AI cannot decide which criteria are genuinely necessary for the role rather than habits or preferences copied from an old advert.
  • AI cannot take responsibility for whether a question or scoring rule creates indirect discrimination in your recruitment process.
  • AI cannot know your organisation's approved wording for reasonable adjustments, data retention or candidate communications.
  • AI can produce a neat scoring table that gives false precision to a judgement the hiring panel still has to own.

Even on a YES, the friction has a name: legal accountability, judgement under ambiguity and context depth.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs2
Verification2
Liability1
Effort delta2
Total9 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT create a pre-screening questionnaire for job applicants?
Yes. It can turn a job description and confirmed essential criteria into questions, response formats and an objective first-stage scoring guide. A hiring manager or HR colleague must check that every question is relevant and fair before applicants see it.
What questions should I ask in a pre-screening questionnaire?
Ask only about genuine job requirements, such as relevant experience, required qualifications, practical availability or the ability to meet stated working arrangements. Do not use the form to ask about protected characteristics or unrelated personal circumstances.
Can AI make a fair applicant screening questionnaire?
AI can help produce consistent wording and a criteria-based structure, but it cannot guarantee that the criteria or scoring method are fair. Your hiring team remains responsible for checking discrimination risks, reasonable adjustments and how answers will affect progression.
Is it legal to use AI to screen job applicants in the UK?
Using AI to draft a questionnaire is not the same as allowing it to make employment decisions, and your organisation remains accountable for the process. Check the questions, scoring and use of applicant data with HR or an employment-law specialist, because this is not professional advice.

Nearby answers

All Job ads & screening rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.