Home · Business · HR & People · Onboarding
As of 13 August 2026, AI can create questions for a new employee's probation review.
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 ita colleague
What the alternative costsAn HR adviser or employee relations specialist can tailor the review process, but no price comparison is provided here.
If this goes wrong: the questions are generic or unfairly focused, and you revise them before the meeting or ask HR to check them.
What to actually do
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.
Use a tool built for this
Second choiceDo it yourself
The distant thirdA chat interface, chat-fluent skill, and roughly 15 minutes until you can act on the result.
How to actually do it
- Open the employee's job description, agreed objectives, probation policy and any review form used by your organisation.
- Gather factual examples from the probation period, including completed work, missed objectives, feedback, training provided and support requested.
- Paste the prompt into a chatbot and replace each bracketed slot with the role, probation length, objectives, factual notes and relevant policy.
- Ask the chatbot to produce the questions, then remove any question that assumes misconduct, introduces an unsupported fact or asks about an irrelevant personal matter.
- Compare the remaining questions with the job objectives and probation policy, then send the final list to your HR contact or a suitable colleague for a fairness and process check before the meeting.
Prompt
Create a fair, practical set of questions for a probation review for [JOB TITLE] after [LENGTH OF PROBATION]. The review should assess the agreed objectives, quality of work, reliability, collaboration, communication, support needed and next steps. Use these role objectives: [PASTE OBJECTIVES]. Use these factual observations and examples: [PASTE NOTES]. Use this relevant company policy or review framework: [PASTE POLICY OR FRAMEWORK]. Write: 1. A short opening question that invites the employee's own view. 2. Ten open questions grouped under clear headings. 3. Separate questions for achievements, missed objectives, support or training, and future priorities. 4. Two questions for the manager to check whether expectations or resources were unclear. 5. A final question about the employee's view of the probation outcome and next steps. Do not invent facts, performance issues or legal requirements. Do not turn assumptions into questions that imply blame. Keep every question specific to the supplied objectives and evidence. Avoid questions about protected characteristics or personal matters unless they are clearly relevant, lawful and covered by the supplied policy. Mark any area where the supplied information is too thin to write a fair question. Use plain UK workplace English.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
What it gets wrong
- AI cannot know whether the objectives were realistic, clearly explained or changed during the probation period.
- AI cannot distinguish a genuine performance issue from a manager's incomplete or biased account of events.
- AI cannot take responsibility for the probation outcome or any employment action that follows.
- AI cannot replace HR's judgement on a disputed process, reasonable adjustments or a possible grievance.
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.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 1 |
| Liability | 1 |
| Effort delta | 2 |
| Total | 8 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT write probation review questions?
- Yes. It can turn the role objectives, factual notes and review policy into a structured set of questions, but you must check the wording before using it.
- What should I give AI to create probation review questions?
- Give it the job objectives, the length of the probation period, relevant company policy and specific observations from the period. Do not ask it to fill gaps by guessing what happened.
- Can AI make probation review questions fair?
- It can help make the wording more balanced by asking about evidence, support and the employee's view as well as shortcomings. It cannot determine whether the underlying objectives, evidence or process are fair, so a manager or HR colleague should check them.
- Can AI decide whether to pass someone’s probation?
- No. AI can organise evidence and draft questions, but the employer must own the decision and follow its probation process. Employment consequences should be checked with HR, especially where the evidence is disputed or a grievance or adjustment may be involved.
Nearby answers
- Can AI automate our employee onboarding workflow?PARTLY
- Can AI create a 30, 60 and 90-day onboarding plan?YES
- Can AI create a process for collecting new starter documents?YES
- Can AI create an IT checklist for a new starter?PARTLY
- Can AI create a plain-English summary of our employee handbook?YES
- Can AI create an onboarding feedback survey?YES
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.