mcp_contract.yaml
Tools, resources, auth scope, and transport boundaries.
Fix the workflow your team still protects by hand.
I turn broken handoffs, approval gaps, and cross-system drag into a workflow your team can trust in production. Start with one workflow. Add Policy OS when speed needs guardrails.
How I Work
Start with the workflow creating the most drag. Add approvals as the risk rises. Extend only when several systems have to stay in sync.
1
Lane 1
Workflow Infrastructure
I map the rules, owners, and handoffs around the workflow slowing your team down most.
2
Lane 2
Policy OS
I add approvals, release checks, blocked states, and incident review so automation stays trustworthy as it expands.
3
Lane 3
Enterprise Extension
I build the control layer for workflows that cross systems, teams, or compliance boundaries.
What's Included
Each lane answers three questions: what gets fixed first, what needs review, and what your team inherits after launch.
Workflow Infrastructure
One painful workflow rebuilt with clear rules, cleaner handoffs, and safer automation.
Includes
- Workflow implementation
- Business-rule mapping
- Auth and access setup
- Runbook and handoff artifacts
The real product
Policy OS
The approval and oversight layer that keeps a live workflow trustworthy as volume, risk, and exceptions increase.
Includes
- Pre-release quality gates
- Policy and approval boundaries
- Postmortem loops
- Monthly tuning
Enterprise Extension
Cross-system control for workflows that need audit trails, recovery paths, and coordination across teams.
Includes
- Cross-system orchestration
- Audit and review controls
- Recovery design
- Architecture support
The Model
Connecting tools is getting easier. Governing live workflows is not.
The hard part is deciding what can run automatically, what needs approval, and what must stop with a reason. That is the work.
- Safe actions run automatically once the workflow and tenant are in good standing.
- Risky actions route to approval instead of becoming cleanup.
- Disallowed actions stop with a reason buyers and operators can both understand.
When a client primarily needs full system development and team onboarding, I refer that engagement to Half Dozen directly.
Reliable workflows are the product. Operational leverage is the outcome.
Governed Execution
Policy OS
Hub MCP routes the request, and Policy OS decides what can run automatically, what waits for approval, and what stops with a reason.
Client LLM
Ops Inbox
Background Agent
Routes
Hub MCP Tenant, host, session
Decides
Policy OS Reason-coded governance
Auto-allowApprovalBlock
CRM
ERP
Workflow System
Safe actions run fast. Risky actions route to approval. Disallowed actions stop with a reason.
Operating Artifacts
What makes the workflow dependable
The buyer promise is backed by explicit contracts, runbooks, and release evidence, not by founder memory or hidden prompts.
mcp_
agent_contract.yaml
Allowed actions, approvals, escalation triggers, and operating limits.
outcome_contract.md
Success metrics, fallback triggers, and ownership boundaries.
runbook.md
Recovery steps, operator lanes, and rollback expectations.
golden-task checks
Regression evidence that keeps releases tied to real workflow behavior.
Map the workflow your team still protects by hand.
In one session, I will map the handoffs, approval points, failure modes, and artifact bundle the workflow needs.