Hiring Screen Assistant With Fairness Guardrails

Design an assistant that helps structure applications without making decisions.

Added October 15, 2026. Written with AI assistance and checked for clarity and placeholders; not reviewed by a lawyer, accountant, clinician or other professional. How these prompts are made

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Design an assistant that helps a recruiter organise applications for [ROLE]. Job criteria in order of importance: [JOB_CRITERIA]. Application materials: [MATERIALS]. Decisions that must stay with people: [HUMAN_DECISIONS]. Policies on fairness: [FAIRNESS_POLICY].

The assistant may only summarise evidence against the stated criteria, quote the application, and list questions for interview. It must not rank people, infer age, gender, ethnicity, health, family status or other protected traits, penalise career gaps, or use name, photo or address. Write the instruction block, the output template (criterion, evidence quote, gaps, interview question), and a bias check that scans the output for forbidden inferences. Provide a calibration routine: run three invented applications, compare with two human reviewers, and note differences. Add logging and retention rules and a candidate-facing note describing how assistance is used [VERIFY with legal and HR].

Include a short list of tests, such as identical applications with different names, to check the assistant behaves consistently.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.