What it is
The build plan for the full reading layer: three narrow agents — intake, ledger, protocol — wired via MCP to the tools you already run, wrapped in a governance layer your team can operate without you. Includes the tool-to-permission mapping (least privilege), the governance layer (consent capture, approval gates, audit trail), explicit per-agent guardrails, SOPs your team can run without you, and a 21-day rollout that switches one agent on per week, governance first. Assumes you already know what an agent and MCP are — if not, start with the Field Guide.
Who it's for
For practitioners scaling 1:1 work without scaling burnout.
Best for
- You run a coaching, nutrition, functional-medicine or longevity practice.
- You want to use AI as a delivery layer — not replace your clinical judgement.
- You're done re-explaining the same protocol in every consult.
Not the right fit if
- You want a fully managed software product — this is a build-it-yourself system.
- You're not ready to put your method in writing.
Audience: Practitioners · Domain: ai-literacy
Inside · paste-ready blocks
ai-agentsmcpmodel-context-protocolpractitionergovernanceai-stackwellness-practice
Preview
Three narrow agents beat one broad one. Each has a single job, its own boundary, and its own approval gate. They pass work down the line — intake feeds the brief, the ledger agent adds pattern context, the protocol agent drafts — and you sign off at each step.
How to use it
🔒 The step-by-step guide unlocks after purchase.