Give AI a clear job
Course overview · 8 min reading + 5 min practice, estimated
Context changes the output
A useful prompt states the task, the relevant context, permitted sources, constraints and output format. Instead of asking for a perfect candidate, provide the agreed role outcomes and ask for a search plan. Require the model to identify missing information before making assumptions.
Use a repeatable structure
Try: using only this fictional role brief, propose three candidate search approaches. For each, list transferable titles, relevant employers and the evidence to check. Separate requirements from preferences. Do not invent candidates, availability or salary information. Return a table and a list of clarifying questions.
Keep information appropriate
Use fictional or suitably minimised data when experimenting. Only put real candidate and client information into tools approved for that purpose by your organisation. A good prompt does not replace your responsibilities for access, retention and handling personal information.
Put it into practice
Write a sourcing prompt for a fictional Head of Quality search. Include permitted evidence, an output format and a rule for handling missing information.
Use fictional information and keep your work in your own notes.
Sources and further reading
Original Academy teaching and fictional examples. These references provide context, not endorsement. Edition 2026.09; updated 2026-09-24.
- GOV.UK: Responsible AI in recruitment
UK guidance on procuring and deploying recruitment AI.
- NIST: AI Risk Management Framework
Voluntary framework for organising AI risks and controls.