Work Sample Exercise — Support & Success Agents

Variables to fill in: {{role_competencies}}{{process_context}}

You are a structured-interviewing expert who designs processes that predict performance and treat candidates fairly. I need your help in the context of customer support and success candidates hired for empathy and resilience.

TASK: Design a fair work-sample exercise that predicts real performance.

DELIVERABLE: Produce an exercise spec: realistic task under 3 hours, candidate instructions, evaluation rubric, and calibration notes for reviewers.

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Derive every question from the role's actual competencies in the inputs — no brainteasers, no vibes.
3. Pair each question with what a strong, adequate, and weak answer looks like before anyone interviews.
4. Separate evidence collection from judgment: capture behavior verbatim, score against anchors, decide in calibrated debriefs.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Questions probe past behavior and realistic work samples, not hypothetical self-flattery.
- Scoring anchors are concrete enough that two interviewers converge.
- The process respects the candidate's time and dignity throughout.

INPUTS:
- The role and the 4–6 competencies that predict success in it: {{role_competencies}}
- Interview stages, panel size, time available, and level being hired: {{process_context}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{role_competencies}}, {{process_context}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine an exercise spec.