Home · Business · HR & People · Job ads & screening
As of 13 August 2026, AI can create a candidate persona for a UK vacancy.
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 specialist recruitment software alternative is Manatal, which offers candidate scoring, enrichment and pipeline automation.
If this goes wrong: the persona adds irrelevant or biased criteria, narrowing the applicant pool and distorting how candidates are assessed.
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 approved job description and copy it into a working document, removing confidential candidate information and internal details that are not needed.
- Gather the vacancy's reporting line, team context, working arrangement, location, hiring objectives and agreed selection criteria from the hiring manager.
- Paste those details into the prompt, replacing every bracketed slot and keeping essential and desirable criteria separate where the team has already agreed them.
- Paste the completed prompt into ChatGPT, Claude or Gemini and ask for the candidate persona.
- Compare each essential criterion in the persona with the approved job description and remove any requirement that is not necessary to perform the role.
- Ask a colleague involved in fair recruitment to check the persona for stereotypes, unsupported assumptions and unnecessary barriers, then send the approved version to the hiring team for sign-off before using it in screening or interviews.
Prompt
Create a candidate persona for this UK vacancy using only the information I provide. Vacancy title: [TITLE] Job description: [PASTE JOB DESCRIPTION] Company and team context: [PASTE CONTEXT] Reporting line: [ROLE] Working arrangement and location: [DETAILS] Hiring objectives for the first 6 to 12 months: [OBJECTIVES] Selection criteria already agreed by the hiring team: [CRITERIA] Produce: 1. A short summary of the person who could succeed in the role. 2. The measurable outcomes they need to deliver. 3. Essential skills and experience, each linked to a stated job requirement. 4. Desirable skills and experience, clearly separated from essentials. 5. Behaviours and working preferences relevant to the role, without stereotypes. 6. Evidence to look for in a CV, application or interview. 7. A list of criteria that should not be used because they are irrelevant, speculative or likely to exclude people unfairly. 8. Five neutral interview questions tied to the essential criteria. Do not invent company facts, salary, qualifications, experience, motivations or candidate characteristics. Do not infer age, gender, ethnicity, disability, religion, sexual orientation, family situation or other protected or personal characteristics. Do not describe an ideal personality. Flag any missing information instead of guessing. Keep the persona focused on fair, job-related selection and label every assumption.
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 a vague job description reflect the real work and which are inherited wording.
- AI cannot decide whether a qualification or experience requirement is genuinely necessary for this vacancy.
- AI cannot reliably spot every subtle form of bias or exclusion in a persona.
- AI cannot take responsibility for the fairness of your hiring process or for decisions made using the persona.
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.
| 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 create a candidate persona?
- Yes. Give it the vacancy, team context, outcomes and agreed selection criteria, and it can produce a structured persona with evidence to look for. Check every criterion against the actual work before using it.
- What should a candidate persona include?
- Include the role outcomes, essential and desirable skills, relevant behaviours, evidence to look for and neutral interview questions. Leave out invented motivations, personality stereotypes and personal characteristics that are not job-related.
- Can AI make a candidate persona fair and unbiased?
- No tool can guarantee that. AI can flag some unnecessary or stereotyped criteria, but a colleague still needs to check the persona against the actual job and your fair recruitment process.
- Is it legal to use AI for recruitment in the UK?
- You can use AI to draft recruitment material, but you remain responsible for lawful and fair hiring decisions and for how personal data is handled. This is not professional advice; a serious equality or data protection concern needs an employment solicitor or data protection professional.
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.