Watch a candidate orchestrate an AI pair engineer
Copilot Command does not ask whether someone used AI. It measures whether they command it well — delegate clearly, verify before accepting, and catch mistakes. Scroll down to see the score and the evidence behind it.
The assessment loop
Three steps, repeated until the task ships
Inside the browser workspace, candidates work with an AI pair engineer using the same delegate → review → decide flow you will see in the replay below.
Delegate
The candidate hands the AI pair engineer a scoped unit of work — clear instructions, constraints, and acceptance criteria.
Review
The AI returns a concrete code change. The candidate reads the diff, runs tests, and decides whether it is ready to ship.
Decide
They accept, reject, or request changes with feedback. What gets scored is the quality of supervision — not how much AI they used.
Demo mode
This page uses a canned session replay. The score and timeline below use the same views hiring teams see on real submissions, with reviewer-only detail removed.
What happens in this sample session
The candidate is implementing pagination for a user list API. Every candidate on this task works through the same scenario, and not every AI proposal is ready to ship. A strong orchestrator checks the work, pushes back with specific feedback, and only accepts once the change is right.
Tip: watch how the candidate reviews each proposal before deciding, and the feedback they give when they push back.
Panel 1
The orchestration score
After the session, reviewers see an overall orchestration score with a plain-language summary. This is the headline number on the evaluation dashboard.
SkillFoundry is live. Evidence-based results report AI use as descriptive, evidence-backed results instead. Talk to us.
AI Orchestration
- Ran the tests before deciding and rejected a proposal that was not ready to ship.
- Requested a targeted revision with specific feedback before accepting the fix.
What the score reflects
How well the candidate supervised the AI: scoping the work, checking what came back, and making sound accept or reject decisions. Reviewers get the full breakdown with the evidence behind it.
Panel 2
The evidence trail
Every number in the score traces back to specific events in this replay — delegations, diffs, test runs, and decisions. That is what makes the score defensible when a hiring decision is questioned.
Demo replay unavailable.
Ready to see this on your own candidates?
Copilot Command is on by default for organizations that allow AI assistance.