Build a governed AI operating layer for your IT team in 30 days.
Start with ten tenant-tested implementations. Use tested agents where AI belongs. Keep human decisions where it does not. Test every build before it touches real work.
No autonomous access decisions. No autonomous production changes.
The never-automate list is part of the product, and the pack ships the reasons. 100 IT activities are classified into five operating modes, and the boundary between them is a gate, not a suggestion.
If a vendor tells you those numbers should be higher, ask who profits from that answer.
of the 100 classified activities are never automate. The pack ships the reasons, not just the count.
Agent-led with review
AI-assisted
Automate
Never automate
Human only
Five parts. Each one is tested, not asserted.
Structure: vendor-neutral methodology (core/), implementation tested on Microsoft 365 (microsoft/). The methodology binds to modes and gates, not to a vendor; other platforms are roadmap, not in this zip.
10 tenant-tested agents67 runs
Built and run in Microsoft 365 Copilot Agent Builder against pre-calculated answer keys: 67 counted runs, and the four defects found on the way are documented in the pack, not hidden. Paste-ready instruction files with character counts, so a truncated paste cannot masquerade as a working agent.
Fixtures and answer keys included
The same instruments the testing used, so "it works on my tenant" is something you prove in an afternoon and re-prove after every platform change.
100 IT activities classified5 modes
Into five operating modes: 40 agent-led with review, 29 AI-assisted, 16 automate, 13 never automate, 2 human only. If a vendor tells you those numbers should be higher, ask who profits from that answer.
50 ready-to-run prompts, 11 gated workflows
A governance page with mechanisms instead of posters, an AI estate register, and a 30-day sprint with a gate at the end of every week.
A 21-page Playbook PDF and a 10-tab workbook2 formats
The 100-row map with your own posture, priority and owner columns, the pre-filled estate register, the full test ledger, and the value scorecard your IT manager reads at day 30.
Honesty page included
TESTING-SCOPE states exactly what the testing establishes and what it does not.
Deploy times are estimates for a first-time builder; the author's expert build time is not your first build, and the pack says so.
Same zip. Different usage rights.
Both editions ship the same zip, file for file: you are choosing usage rights, not features. Licensed, not sold.
- Deploy the agents in a tenant you work in
- Adapt everything for what you personally do
- No team redistribution, no resale, no public republication
- Share the pack across your IT function
- Multiple practitioners can build from it
- No resale, no public republication, no delivering it as paid training
Both editions ship the same zip, file for file. Click Buy, then confirm Individual or Organization Edition before you pay.
Pair it with the deeper dives.
The Stack is the build layer. These go one level deeper on rollout and hardening. Each is a standalone artifact.
IT AI Quickstart Pack
A working slice of the same methodology: 50 engineered prompts and one complete tested agent, for one named purchaser.
The Copilot Hardening Baseline
176 checks for the Microsoft 365 Copilot admin surface. Each one names the baseline to set and how to prove it.