The Assessment

How it works

Proofency runs a live work simulation with 30–55 minutes of working time, depending on assessment tier, to observe demonstrated behavior, not theoretical knowledge. A separate five-minute grace period is available for submission. The assessment evaluates candidates inside a realistic work environment with a live AI assistant.
1

Context and Brief

The candidate is placed into a scenario specifically designed for their role, industry, and seniority band. They are given raw context, constraints, and a deliverable objective.

2

Prompting and Delegation

The candidate must direct an AI assistant to complete the task. We evaluate Agentic Judgment (the quality of the delegation) and Prompt Quality. Agent outputs are drafts, and candidates remain responsible for what enters their deliverable.

3

Evaluation and Catching Errors

Agent outputs can contain errors. The candidate must review the work before accepting it, especially where a mistake would matter. Critical Evaluation measures the diligence shown in that review.

4

Judgment and Override

Upon spotting an error, the candidate must actively override and correct it. We capture the complete timeline, immutable work revisions, and final submission to measure Output Quality based on unverified AI-originated substance versus verified candidate corrections.

5

The Final Submission

Once submitted, the evidence is captured on an append-only timeline. A controlled outcomes-grading process uses temperature-0 model calls with a median-of-three consensus on sampled graders to produce a final AI Collaboration Index.

See what we measure