Home · Business · HR & People · Interviewing & assessment

YES

As of 13 August 2026, AI can design a practical interview task.

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 costsThe available tool information gives no comparable alternative price for a human interview-task designer.

If this goes wrong: candidates complete an irrelevant or inconsistent exercise, and your hiring process produces weak evidence or an avoidable fairness complaint.

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 out the role purpose, essential duties, seniority and required competencies.
    2. Ask the hiring manager for the time limit, interview format, permitted equipment or systems, expected candidate output and any accessibility adjustments.
    3. Paste those details into the prompt and ask the chatbot to produce the candidate brief, interviewer instructions, rubric, follow-up questions and pilot checklist.
    4. Run the draft task yourself or with a colleague using only the materials candidates will receive, and record whether the instructions and time limit work.
    5. Compare each scoring criterion with the job description and remove any criterion that is not necessary for the role or cannot be observed consistently.
    6. Give the same final brief, information and time limit to a colleague for a blind review, then revise the task before sending it to candidates.

    Prompt

    Design one practical interview task for the role described below.
    
    Role: [job title]
    Organisation and work context: [brief description]
    Level: [seniority]
    Core competencies to assess: [list]
    Essential technical or practical skills: [list]
    Interview format: [in person, remote or hybrid]
    Time available for the task: [duration]
    Materials, systems or equipment candidates may use: [list]
    Candidate experience and accessibility requirements: [details]
    What a strong response should demonstrate: [details]
    What the task must not require: [details]
    
    Produce:
    1. The purpose of the task and the competencies it assesses.
    2. A candidate-facing brief written in plain UK English.
    3. Exact instructions, inputs, deliverables and time limit.
    4. Any information the interviewer must provide consistently to every candidate.
    5. A scoring rubric with four observable criteria and clear descriptions for weak, acceptable and strong performance.
    6. Follow-up questions that test the same competencies without introducing new requirements.
    7. A short accessibility and fairness check.
    8. A pilot checklist for testing that the task can be completed within the stated time.
    
    Use only the information supplied. Do not invent company facts, technical requirements or candidate data. Keep the task relevant to the role, avoid unnecessary personal or protected-characteristic information, and distinguish observable evidence from assumptions about personality. Flag any decision that requires human judgement rather than presenting it as settled.

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

What it gets wrong

  • AI cannot know which behaviours genuinely matter in your workplace beyond the information you provide.
  • It cannot establish that the task predicts job performance without piloting it and comparing the evidence with later work.
  • It cannot decide whether an adjustment is sufficient for a particular candidate or situation.
  • It cannot carry responsibility for consistency, discrimination risk or the final hiring process.
  • It often adds generic complexity, so unnecessary steps and impressive-sounding criteria need removing.

Even on a YES, the friction has a name: judgement under ambiguity, legal accountability 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
Verification1
Liability1
Effort delta2
Total8 / 10

FAQ

Can ChatGPT design an interview task?
Yes. It can draft a practical exercise, candidate instructions, interviewer guidance and a scoring rubric from a job description and clear constraints. You still need to test the task and own the final assessment.
Will an AI-designed interview task be fair?
Not automatically. Check that every requirement is necessary for the role, that candidates receive the same information and time, and that reasonable adjustments are possible.
What information should I give AI to design an interview task?
Give it the role duties, competencies, seniority, task duration, interview format, permitted materials, expected output and accessibility requirements. Include what candidates must not be asked to disclose or use.
Can I use an AI-generated interview task in a UK hiring process?
You can use AI to draft the task, but a human should approve, pilot and administer it consistently. The employer remains responsible for the assessment process and its employment-law consequences.

Nearby answers

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.