ai-docs/docs/ai/governance.md
2026-02-10 14:24:09 -06:00

38 lines
1.1 KiB
Markdown

# Governance, Privacy, and Policy
## Allowed Data
- Public information or approved internal content.
- Code that is already in approved repos.
## Handle With Care
- Customer data or identifiers.
- Security-sensitive configuration.
- Anything not explicitly approved by policy.
## Forbidden Data
- Secrets, credentials, or personal data.
- Non-approved proprietary information.
## Safe Prompt Examples
- "Summarize this public API and propose tests."
- "Refactor this function without changing behavior."
## Redaction Tips
- Remove secrets before pasting.
- Replace real identifiers with placeholders.
- Use minimal context required for the task.
### Example Redaction
Before: "User ID 928374 has email jane@company.com and token ABC123."
After: "User ID <USER_ID> has email <EMAIL> and token <TOKEN>."
## Compliance Expectations
- Follow org security policies and data handling rules.
- Use AI as assistance, not authority.
## Ownership
If you are unsure about data classification, escalate before using AI.
### Example Question
"Is it ok to share this log snippet with user IDs in Copilot?"