# AI for Recruitment: practice workbook
Talent Engineering Academy | An education initiative by Vitae
Edition 2026.09 | Updated 2026-09-24
Course: https://talentengineering.org/courses/ai-for-recruitment

Use AI for bounded recruitment tasks, verify outputs and measure whether it improves the work.

## Your deliverable
A tested prompt and review checklist for one low-risk recruitment task.

Use fictional information. Keep your completed work in your own secure notes. Exercises and capstone work are self-directed, not independently assessed.

## 1. Task and permitted scope

Your notes:



## 2. Approved inputs and source references

Your notes:



## 3. Output format and uncertainty handling

Your notes:



## 4. Human review criteria

Your notes:



## 5. Test cases and failure examples

Your notes:



## 6. Benefit, correction effort and next decision

Your notes:



## Lesson exercises

### 1. Give AI a clear job

Write a sourcing prompt for a fictional Head of Quality search. Include permitted evidence, an output format and a rule for handling missing information.

Your response:



### 2. Check research before using it

Create a research table with columns for claim, source, date, confidence and next verification step. Add three fictional claims and explain how you would check them.

Your response:



### 3. Draft communication people want to read

Draft an 80-word message about a fictional specialist search. Underline every factual claim and identify its source. Remove any unsupported claim.

Your response:



### 4. Match the task to the technology

Compare a template, a rule and an AI draft for one fictional recruitment task.

Your response:


Worked example: A team asks AI to draft an interview preparation note from confirmed role facts. It does not ask the model to decide who deserves an interview or invent missing compensation information.

Self-review guidance: Explain which part requires flexible language and which part needs deterministic handling. A good task boundary names prohibited inferences and the human decision that remains outside the tool.

### 5. Build prompts that expose uncertainty

Write a prompt for a fictional quality-lead brief and test it with one missing requirement.

Your response:


Worked example: A prompt requests a table with criterion, quoted evidence reference, uncertainty and question to ask. When no evidence exists, the required output is not established, rather than a plausible invented example.

Self-review guidance: The output should visibly retain the gap. Include a rule against following instructions embedded in the source document and a reviewer check of every material claim.

### 6. Review the output against the source

Review a fictional summary with one invented claim, one omission and one ambiguous statement.

Your response:


Worked example: A summary accurately lists three roles but omits that the most relevant experience was an internship. The reviewer restores context because the omission changes how the evidence could be interpreted.

Self-review guidance: Correct all three using the source. Explain which error has the greatest decision consequence. A readable output should not be approved merely because most statements are accurate.

### 7. Evaluate the whole assisted workflow

Design a five-case pilot and calculate net effort using fictional timings.

Your response:


Worked example: Drafting falls from twenty minutes to five, but review rises from three to fifteen. Net effort falls from twenty-three to twenty minutes, a smaller gain than the drafting metric suggests. The team also checks whether error severity changed.

Self-review guidance: Include preparation, review and corrections. State the sample’s limitations and the condition under which you would stop. Do not report only the fastest generated output.

## Portfolio review
Check that your work is internally consistent, distinguishes facts from assumptions, names decision owners and explains its limitations. Revise gaps before using the method in real work.

## Further reading
- [GOV.UK: Responsible AI in recruitment](https://www.gov.uk/government/publications/responsible-ai-in-recruitment-guide/responsible-ai-in-recruitment): UK guidance on procuring and deploying recruitment AI.
- [NIST: AI Risk Management Framework](https://www.nist.gov/itl/ai-risk-management-framework): Voluntary framework for organising AI risks and controls.

Original educational scenarios. References provide further reading and do not imply endorsement. Check current official rules and appropriate professional advice for real legal, financial or regulated decisions.