Home · Business · HR & People · Onboarding

YES

As of 13 August 2026, AI can create check-in questions for an employee on probation.

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

Can you do it?

5 minutesto a draft.

15 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ityou

What the alternative costsThe supplied tool information gives no price for a human alternative to drafting these questions.

If this goes wrong: the questions are generic, poorly timed or unfairly focused, and you can replace them before the meeting or correct the discussion in it.

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 15 minutes until you can act on the result.

    How to actually do it

    1. Open the employee's job description, probation objectives, review timetable and any required internal review form.
    2. Gather the factual examples, completed work, feedback and support already provided that are relevant to the review stage.
    3. Paste those materials into the prompt, replacing each bracketed slot and removing personal information that the chatbot does not need.
    4. Ask the chatbot to produce the questions, then delete any question that assumes an outcome, raises an irrelevant personal matter or cannot be answered from the role and objectives.
    5. Compare the remaining questions with the internal review form and your organisation's probation process, then send the final agenda to the employee in line with that process.

    Prompt

    Create a practical set of questions for a probation check-in meeting for this employee.
    
    Role: [job title and brief role description]
    Probation length and review stage: [for example, week 6 of a 6-month probation]
    Agreed objectives: [paste the objectives]
    Key responsibilities: [paste the relevant responsibilities]
    Evidence or topics to discuss: [paste factual examples, achievements or concerns]
    Meeting length: [for example, 30 minutes]
    Organisation or team process: [paste any required review headings or policy wording]
    
    Write 10 to 12 open questions, grouped under: progress against objectives, support and development, workload and working relationships, and next steps. Include questions for the employee and a short separate list for the manager to ask themselves before the meeting. Keep the wording neutral, specific and suitable for a UK workplace. Do not make assumptions about performance, health, disability, family circumstances, protected characteristics or the outcome of probation. Do not provide legal conclusions or recommend dismissal. Mark any question that needs my factual input with [CHECK]. Avoid repetitive, leading or accusatory questions.

    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 parts of the employee's performance are genuinely important unless you provide accurate objectives and examples.
  • AI cannot judge whether a question will feel fair, proportionate or appropriate for the relationship between this manager and employee.
  • AI cannot identify all relevant workplace context, including previous informal conversations, team dynamics or support already offered.
  • AI cannot take responsibility for the meeting, the record of what was said or any decision about passing probation.

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

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
Liability2
Effort delta2
Total10 / 10

FAQ

Can ChatGPT create probation review questions?
Yes. Give it the role, agreed objectives, review stage and factual topics, and it can draft a usable question set quickly. You still need to remove assumptions and check the questions against your organisation's process.
What should I ask an employee at a probation check-in?
Ask about progress against agreed objectives, what is going well, what is unclear, what support is needed and what should happen before the next review. Questions should be tied to the role rather than personal circumstances or an assumed outcome.
Can AI make probation questions fair and unbiased?
It can help make wording more neutral and flag leading or repetitive questions, but it cannot assess the whole employment context. You must check that the questions use consistent standards and do not rely on irrelevant personal information.
Can AI decide whether someone passes probation?
No. AI can organise evidence and draft discussion questions, but the manager and employer must own the assessment and decision. Keep the decision tied to the documented role expectations, evidence and applicable workplace process.

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.