Home · Business · HR & People · Interviewing & assessment
As of 13 August 2026, AI can generate competency-based interview questions.
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 costsA purpose-built recruitment platform such as Manatal supports candidate scoring, enrichment and pipeline automation.
If this goes wrong: candidates are assessed against irrelevant or unfair questions, producing inconsistent decisions and a possible employment dispute.
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 current job description and copy it into a working document, removing confidential candidate information and anything unrelated to the role.
- List the competencies the role genuinely requires, using the employer's existing competency framework where one exists, and note the evidence expected for each.
- Paste the job description, competency list, seniority, interview format and panel details into the prompt, then run it in a chatbot.
- Compare every generated question with the competency it claims to test and delete questions that assess personality, background or personal circumstances rather than job evidence.
- Check the questions against the organisation's recruitment policy and UK equality requirements with the hiring manager or HR colleague, then agree one consistent set for all candidates.
- Test the wording with the interview panel by asking what evidence would count as a strong, acceptable or weak answer, and revise questions where panel members would score the same answer differently.
- Send the final question set and scoring notes to the panel with instructions to record evidence rather than impressions.
Prompt
Create a competency-based interview question set for this role. Role title: [ROLE TITLE] Job description: [PASTE JOB DESCRIPTION] Competencies to assess: [LIST THE COMPETENCIES] Seniority: [LEVEL] Interview length and format: [DETAILS] Interview panel: [ROLES OR FUNCTIONS] For each competency, provide: 1. One main behavioural question that asks for a specific past example. 2. Two neutral follow-up probes that work for candidates with different backgrounds. 3. What a strong, acceptable and weak answer would demonstrate, without requiring one specific career history. 4. Evidence the panel should record. Use plain UK English. Make every question directly relevant to the role and avoid questions about protected characteristics, health, family circumstances, age, religion, nationality, disability, pregnancy, trade union activity or other personal matters unrelated to the job. Do not invent details about the employer or role. Flag any competency that is vague, duplicated or not supported by the job description. Keep the questions consistent across candidates and separate the interview questions from the panel scoring notes.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
What it gets wrong
- AI cannot decide whether the chosen competencies are actually necessary for the role.
- AI cannot reliably spot every indirect form of discrimination or understand the employer's full recruitment history.
- AI cannot replace a consistent scoring process owned by the interview panel.
- AI cannot take responsibility for a question that produces an unfair hiring outcome.
- AI cannot know which examples will be credible in the organisation's real working environment without context from your team.
Even on a YES, the friction has a name: legal accountability, judgement under ambiguity and verification cost.
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 competency-based interview questions?
- Yes. It can turn a job description and competency list into behavioural questions, follow-up probes and scoring notes. You still need a hiring manager or HR colleague to check relevance, fairness and consistency.
- How do I ask AI to create competency-based interview questions?
- Give it the job description, the competencies being assessed, the seniority, interview format and evidence expected. Tell it to use the same questions for candidates, avoid personal matters and flag competencies that are vague or unsupported.
- Are AI-generated interview questions legal in the UK?
- The use of AI does not make an interview process lawful by itself. Check every question for relevance and discrimination risk, and keep responsibility with the employer and interview panel.
- Can AI score answers to competency-based interview questions?
- AI can organise a scoring rubric or summarise evidence if you provide an approved framework. It should not make the hiring decision, infer traits from wording or replace the panel's documented assessment.
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.