Merit AC™
Library / AI policy and governance

Giving an AI agent access to company systems

A vendor-neutral playbook for connecting an AI agent to email, files, CRM or code: its own identity, narrow scopes, read-only first, approval gates, logging, a kill switch and quarterly review.

Playbook · 25 min · Members

What's inside
  • The eight controls
  • 1. A separate identity for each agent
  • 2. Least-privilege scopes
  • 3. Read-only first
  • 4. Approval gates for writes
  • 5. Logging
  • 6. A kill switch you've tested
  • 7. A named human owner
  • 8. Quarterly access review
  • Access record template
  • Worked example

All 36 pieces with AI Skills Academy · $49/mo

  • Every playbook, template, checklist and worksheet in the Library, and each new one as it's added
  • The full 30-lesson course, the Agent Authority Scanner and your evidence package
  • Six governed agents to download and run in Claude Code
Join · $49/moWhat's in the Academy

Cancel any time from the billing link in your receipt.

More in AI policy and governance

Acceptable use policy for AI at workTemplate · 25 min · FreeAI data classification for staffWorksheet · 15 min · MembersAI incident report and response runbookTemplate · 20 min · MembersApproving a new AI toolChecklist · 20 min · Members