Sep 3, 2026
We Did Not Teach HR to Prompt AI. We Built a Live Résumé-Screening Agent With Them.
A live workshop. A real HR bottleneck. One explainable AI agent built with the team.
1,000 Résumés. One Human Decision Queue.
A team walked into our workshop with a real HR bottleneck: more than 1,000 résumés and no fast, consistent way to review them.
We did not give them another tool demonstration. We built a working résumé-screening agent with Claude, live in the room.
Takeaway
Do not ask AI to choose the candidate. Ask it to prepare better evidence for a human decision.
We did not automate hiring.
We redesigned the first review.
The agent had one disciplined job: turn an unstructured pile of applications into a consistent, explainable shortlist for people to review.
Extract the same job-relevant evidence from every résumé
Score only against an approved role scorecard
Flag missing, uncertain or contradictory information
Create a ranked queue for human review
Takeaway
The right role for AI here is decision support, not automated rejection.
The workflow came before the tool.
1. Define success
We first agreed on what a useful output should look like for the recruiter and hiring manager.
2. Turn judgement into a scorecard
The team converted experience, skills and must-have requirements into explicit criteria that could be checked consistently.
3. Give Claude the right context
The role description, scorecard and operating rules became the agent’s working context. The prompt was only one part of the system.
4. Test it with people
The team reviewed the evidence, challenged the scores and improved the instructions. Human judgement stayed inside the loop.
Takeaway
A dependable AI agent begins with a clear process, not a clever prompt.
Human control was built in.
Hiring decisions affect people. That is why the boundaries of the agent mattered as much as its speed.
Where the agent stopped
No inference of protected characteristics
No final hiring or rejection decision
No unsupported assumptions
Every score required visible evidence
Takeaway
If a decision matters, make the evidence visible and keep a person accountable for the outcome.
The room learned a reusable method.
The real result was not only one HR agent. The team learned how to move from a business problem to a controlled AI workflow they could test and improve.
Problem → Process → Context → Agent → Human Control → Business Measure
Takeaway
Start with the workflow that needs to change. Choose the AI only after the work is clear.
Measure work, not novelty.
A successful pilot should improve the quality and pace of work. We would track:
Screening time per application
Agreement between the agent and human reviewers
Correction rate after human review
Shortlist quality
Audit and bias exceptions
Takeaway
The question is not whether the agent looks impressive. The question is whether the workflow gets measurably better.
Build the agent around your business.
Our workshops use your team’s real workflows, decisions and constraints. Participants build something useful during the session and leave with a method they can use again.
Invite Team Being Relentless to build a live AI agent with your team.