1 min lesson
Self-scoring against the ADM bar
Describe what "Now grade them across five dimensions, with a hard look at anything you overclaimed" changes in practice.
Step 1 of 3
Four deliverables done. Now grade them across five dimensions, with a hard look at anything you overclaimed.
Score each deliverable 1 to 5 and read the consistency check, because a loop that contradicts itself across deliverables fails even if each piece looks strong.
Learn more
Advanced table
The five-dimension rubric
The five-dimension rubricScore each 1 to 5
- Dimension
- Product depth
- A 5 looks like
- You speak Tab, Agent, context,
.cursor/rules/and MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition. fluently and tie each to a workflow outcome - A 2 looks like
- Generic "the AI helps developers" with no specific Cursor capability
- Dimension
- Rollout / operational rigor
- A 5 looks like
- Phased plan with metrics and leading indicators per phase, risks named with mitigations
- A 2 looks like
- A list of activities with no numbers and no sequencing logic
- Dimension
- Data reasoning
- A 5 looks like
- You segmented the stall and traced each action to a specific signal
- A 2 looks like
- You reached for "more training" against an aggregate number
- Dimension
- Executive communication
- A 5 looks like
- EBR opens in the sponsor's goals, pairs data with stories, surfaces renewal early
- A 2 looks like
- A dashboard read-out with no narrative the CTO would repeat
- Dimension
- Truth-seeking honesty
- A 5 looks like
- You refused to inflate ROIReturn on Investment. The value gained versus what it cost, the language an economic buyer funds deals in. Press Enter for the full definition. and flagged your own uncertainty
- A 2 looks like
- You promised a productivity multiplier you can't defend
| Dimension | A 5 looks like | A 2 looks like |
|---|---|---|
| Product depth | You speak Tab, Agent, context, .cursor/rules/ and MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition. fluently and tie each to a workflow outcome | Generic "the AI helps developers" with no specific Cursor capability |
| Rollout / operational rigor | Phased plan with metrics and leading indicators per phase, risks named with mitigations | A list of activities with no numbers and no sequencing logic |
| Data reasoning | You segmented the stall and traced each action to a specific signal | You reached for "more training" against an aggregate number |
| Executive communication | EBR opens in the sponsor's goals, pairs data with stories, surfaces renewal early | A dashboard read-out with no narrative the CTO would repeat |
| Truth-seeking honesty | You refused to inflate ROIReturn on Investment. The value gained versus what it cost, the language an economic buyer funds deals in. Press Enter for the full definition. and flagged your own uncertainty | You promised a productivity multiplier you can't defend |
Score yourself against the 5 column, not the 2 column.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
diagram: signal-bars
Our ordering for prep, built from the ADM posting. Cursor publishes no scoring rubric.