As of 13 August 2026, AI can create a structured interview scorecard.

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 paste it into a working document, removing confidential candidate information and any requirements that are not part of the approved role.
   2. Gather the hiring manager's approved essential criteria, desirable criteria, interview length, interview stage and existing questions in the same document.
   3. Paste the collected material into the prompt and replace every bracketed slot with the role-specific information, writing "none" where no approved questions exist.
   4. Ask the chatbot to produce the scorecard, then copy the proposed competencies, questions, rating anchors and calculation method into your interview template.
   5. Compare every criterion and question with the approved job description, remove anything the role does not require, and ask HR to check ambiguous criteria, weighting and reasonable-adjustment wording.
   6. Run the scorecard against a fictional or previously completed interview, checking that two interviewers could reach ratings from the recorded evidence rather than from general impressions, then send the approved version to every interviewer before interviews begin.

   Prompt

   Create a structured interview scorecard for the UK role described below.
   
   Role and context:
   [PASTE JOB DESCRIPTION]
   
   Interview stage:
   [DESCRIBE THE STAGE AND LENGTH]
   
   Approved competencies and essential criteria:
   [LIST THEM]
   
   Interview questions already agreed:
   [PASTE THEM OR WRITE NONE]
   
   Create a practical scorecard for interviewers. Include:
   1. Each competency or criterion being assessed.
   2. One or more interview questions linked to each criterion. Keep questions job-related and avoid asking for protected characteristics or irrelevant personal information.
   3. What strong, acceptable and weak evidence would look like for each criterion. Describe observable evidence, not personality labels.
   4. A consistent rating scale from 1 to 5 with plain anchors, where 1 means insufficient evidence and 5 means exceptional evidence relevant to this role.
   5. A notes field for evidence and a separate rating field for each criterion.
   6. A clear method for reaching an overall result without allowing one vague impression to override the recorded evidence.
   7. Any criteria, questions or weighting that appear irrelevant, duplicative, ambiguous or likely to create inconsistent treatment. Explain the concern and propose a neutral revision.
   8. A short interviewer instruction section covering asking the same core questions, recording evidence before rating, handling reasonable adjustments through the approved HR process, and declaring conflicts of interest.
   
   Do not invent requirements, company policies, candidate facts or legal conclusions. Mark missing information as [NEEDS DECISION]. Keep the final scorecard concise enough to use during a live interview. Put the finished scorecard in clear tables or headings, followed by a separate list of decisions that the hiring manager or HR team must approve.

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