An evidence-grounded pilot JSON and source manifest
AI Workplace Quality
Check AI-assisted work against evidence and a clear output contract.
beginner · About 100 minutes · 4 lessons · 8 exercises + 1 project
Your finished work
An evidence-grounded pilot JSON and source manifest
Completion requires every output check to pass. Exact columns, types, values, missing values and duplicate counts all matter. A diagnostic score helps you revise your work.
All examples use original, fictional business data. Your final project starts with 62 source records.
The course
- Start lesson →
1. Extract a usable brief
Turn a source into explicit constraints without inventing details.
- Start lesson →
2. Check claims against evidence
Separate unsupported and contradicted claims.
- Start lesson →
3. Produce a reliable structure
Use a precise schema and stable units.
- Start lesson →
4. Review before handoff
Check a result for evidence, constraints and an explicit limitation.
Put it together
Deliver a grounded pilot brief
62 source records. Apply the business rules, check your output and download a handoff report with your source, answer and results.
Preview your first input
{
"sources": [
{
"id": "S1",
"title": "Pilot brief",
"text": "The fictional Northstar pilot starts 2026-11-02. It covers 12 support agents. The pilot lasts 14 calendar days. Budget is 2400 USD."
},
{
"id": "S2",
"title": "Review policy",
"text": "Morgan owns the review. No customer personal data may enter the pilot. No automation may send customer replies without human approval."
},
{
"id": "S3",
"title": "Results memo",
"text": "The test processed 80 synthetic tickets. 72 had the correct category. Median handling time was 6 minutes. Customer satisfaction was not measured."
}
],
"brief": "Return start_date (string), agents (number), budget_usd (number), source_ids (array).",
"flawed_output": "The pilot starts next month for 20 agents with unlimited budget."
}