Catalogue › Platform Governance

CopilotForge - Platform Governance

Use it in Copilot Cowork: download the Platform Governance plugin for Copilot Cowork and upload it under Customize > Plugins > Upload plugin. How to install.

Govern environments, makers, connectors, agents, deployment, licensing and portfolio visibility.

Layer: assurance
Lead role: Platform Governance Lead
Plugin name: copilotforge-platform-governance

Skill Status Lifecycle Description

ai-admin-monitoring draft Assure, Measure, Scale, Improve Sets up administrative monitoring of the AI estate - new and widely shared agents, policy and exception drift, orphaned solutions, unusual connector use, consumption and capacity trends - reported at estate, zone and business unit level, each signal with an owner. Use when governance relies on finding problems by accident, when the estate grows faster than reviews, or when steering asks what is happening across the platform.

ai-environment-strategy draft Mobilise, Enable, Scale, Improve Sets the environment strategy for AI building as governance zones - personal productivity, team collaboration and managed production - deciding who builds in each zone, its controls and sharing limits, and how a solution moves up a zone. Use when there is no organisation-wide rule for where AI building happens, when experiments become business-critical without controls, or when a team solution needs a governed home.

ai-licensing-and-capacity draft Envision, Mobilise, Scale, Improve Frames the licensing and capacity questions for Microsoft AI - who needs which kind of access, consumption-based usage, Dataverse and platform capacity, growth and cost owners - and gathers demand evidence for the Microsoft licensing guide or a licensing partner, never concluding itself. Use when a rollout or agent build raises licence or capacity questions, when consumption costs surprise budget holders, or before a renewal.

ai-release-policy draft Mobilise, Assure, Launch, Improve Sets the organisation's release policy for agents, flows and AI solutions by risk tier - the evidence, reviewer sign-offs, approver, permitted audience and channels, and post-release review each tier requires - plus rules for widening an audience, emergency changes and exceptions. Use when there is no consistent rule for publishing agents, when release takes the same effort at every tier, or when solutions reach wide audiences without review.

ai-solution-inventory draft Mobilise, Assure, Scale, Improve Builds and keeps current an inventory of agents, flows, Cowork plugins and custom AI solutions across Microsoft 365, Power Platform and Azure - discovered from admin sources, reconciled with the agent portfolio register, with owners, zone, risk tier, sharing reach and review dates, and orphans flagged. Use when nobody can say how many agents exist, when an audit asks for a list, or when orphaned or unregistered solutions need finding.

connector-policy draft Mobilise, Enable, Assure, Improve Writes the organisation-wide data and connector policies for AI building in each zone - business, non-business and blocked connector groups, custom connectors, HTTP and MCP access, web and public knowledge, endpoint filtering - with an exceptions process that has owners and review dates. Use when data policies predate agents, when makers keep requesting blocked connectors, or when AI features such as web grounding or MCP need a policy position.

maker-governance draft Enable, Deliver, Scale, Improve Governs who can build and share agents and flows - maker enablement, onboarding commitments, sharing rights by zone and audience, ownership on creation, handover when makers move on, and the limits that stop personal builds being shared organisation-wide - without ranking makers. Use when agent building is opened to more people, when agents are shared too widely, or when makers leave and their solutions become orphans.

Skill	Status	Lifecycle	Description
`ai-admin-monitoring`	draft	Assure, Measure, Scale, Improve	Sets up administrative monitoring of the AI estate - new and widely shared agents, policy and exception drift, orphaned solutions, unusual connector use, consumption and capacity trends - reported at estate, zone and business unit level, each signal with an owner. Use when governance relies on finding problems by accident, when the estate grows faster than reviews, or when steering asks what is happening across the platform.
`ai-environment-strategy`	draft	Mobilise, Enable, Scale, Improve	Sets the environment strategy for AI building as governance zones - personal productivity, team collaboration and managed production - deciding who builds in each zone, its controls and sharing limits, and how a solution moves up a zone. Use when there is no organisation-wide rule for where AI building happens, when experiments become business-critical without controls, or when a team solution needs a governed home.
`ai-licensing-and-capacity`	draft	Envision, Mobilise, Scale, Improve	Frames the licensing and capacity questions for Microsoft AI - who needs which kind of access, consumption-based usage, Dataverse and platform capacity, growth and cost owners - and gathers demand evidence for the Microsoft licensing guide or a licensing partner, never concluding itself. Use when a rollout or agent build raises licence or capacity questions, when consumption costs surprise budget holders, or before a renewal.
`ai-release-policy`	draft	Mobilise, Assure, Launch, Improve	Sets the organisation's release policy for agents, flows and AI solutions by risk tier - the evidence, reviewer sign-offs, approver, permitted audience and channels, and post-release review each tier requires - plus rules for widening an audience, emergency changes and exceptions. Use when there is no consistent rule for publishing agents, when release takes the same effort at every tier, or when solutions reach wide audiences without review.
`ai-solution-inventory`	draft	Mobilise, Assure, Scale, Improve	Builds and keeps current an inventory of agents, flows, Cowork plugins and custom AI solutions across Microsoft 365, Power Platform and Azure - discovered from admin sources, reconciled with the agent portfolio register, with owners, zone, risk tier, sharing reach and review dates, and orphans flagged. Use when nobody can say how many agents exist, when an audit asks for a list, or when orphaned or unregistered solutions need finding.
`connector-policy`	draft	Mobilise, Enable, Assure, Improve	Writes the organisation-wide data and connector policies for AI building in each zone - business, non-business and blocked connector groups, custom connectors, HTTP and MCP access, web and public knowledge, endpoint filtering - with an exceptions process that has owners and review dates. Use when data policies predate agents, when makers keep requesting blocked connectors, or when AI features such as web grounding or MCP need a policy position.
`maker-governance`	draft	Enable, Deliver, Scale, Improve	Governs who can build and share agents and flows - maker enablement, onboarding commitments, sharing rights by zone and audience, ownership on creation, handover when makers move on, and the limits that stop personal builds being shared organisation-wide - without ranking makers. Use when agent building is opened to more people, when agents are shared too widely, or when makers leave and their solutions become orphans.

Credit

Created by Simon Foote as part of CopilotForge. Content is licensed under CC BY 4.0; keep the credit in each skill's license and authors fields when you share or adapt it. See NOTICE.md in the repository.