Calling a task low risk does not create the access, evidence, or reversal path needed to perform it safely.
The practical check
Ask what the tool is actually allowed to read, suggest, prepare, or change. The answer should come from a capability boundary, not a label.
Where AI fits
AI can map a task into read, draft, suggest, and action capabilities with evidence for each boundary.
The human decision
People grant authority, review exceptions, and decide when a capability should expand.
The lesson
Give a tool the narrowest capability that the evidence and approval process support, then expand authority only when people can account for the consequences.
Bounded agent authority is set out in the Build Log companion through capability evidence, access limits, and a reversal route.
AI Skills
Use this lesson with the AI assistant you already use
Map each task to the narrowest allowed capability and the human approval needed to go further.
Paste the prompt, share only the context needed to answer it, and treat the result as a draft for your review. Do not include confidential information or let an AI assistant make changes without your approval.
Optional: for a visual report and saved memory, run /dxdev first.
Don’t have it? Get it at dxdev.com/skills/dxdev. The prompt works without it.
dxdev LESSON · paste into your AI agent
LESSON: Define Capability Before Autonomy
WHAT TO SHARE:
A de-identified description of the work, current evidence, and the decision you are considering.
ASK YOUR AGENT TO:
1. Separate confirmed facts from assumptions and unanswered questions.
2. Map each task to the narrowest allowed capability and the human approval needed to go further.
3. Identify the narrowest useful next review step.
RETURN:
A short table with the evidence, uncertainty, human-owned decision, and next action.
BOUNDARY: Do not change records, contact anyone, route work, publish content, or act in an external system. A person must review the evidence and approve every consequential step.
