Catalogue › AI Architecture

CopilotForge - AI Architecture

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

Select appropriate patterns and define target architecture across Microsoft 365, Power Platform, Azure and data services.

Layer: assurance
Lead role: AI Solution Architect
Plugin name: copilotforge-ai-architecture

Skill Status Lifecycle Description

ai-identity-design draft Deliver, Assure, Improve Designs the identities an AI solution uses end to end - signed-in users, agent identities, service principals and managed identities - mapping which identity each hop runs under, how consent, scopes and conditional access apply, and who owns each non-human identity. Use when an agent or AI solution calls systems on someone's behalf, when an agent needs its own identity, or when nobody can say whose rights a solution acts with.

ai-integration-patterns draft Deliver, Assure, Improve Chooses how an AI solution connects to business systems - standard or custom connectors, flows as actions, APIs, MCP servers, events, Dataverse or Graph - deciding direction, identity, synchronous or asynchronous timing, write confirmation and failure behaviour for each interface. Use when an agent or AI solution must read from or act in other systems, when an interface list is growing unplanned, or when a write action needs a safe pattern.

ai-non-functional-requirements draft Envision, Deliver, Assure Specifies the non-functional requirements of an AI solution - quality thresholds, latency, availability, capacity, cost per use, resilience, observability, security, retention, accessibility and supportability - scaled to the risk tier, each measurable with an owner. Use when a solution moves from idea to design, when a pilot is about to become a service, or when nobody can say how good, fast or available the solution must be.

ai-reference-architecture draft Mobilise, Deliver, Scale, Improve Maintains a small set of reference architectures for recurring Microsoft AI patterns - knowledge agent, business-data agent with actions, AI-assisted automation, custom Foundry solution - each with components, identity and data flows, mandatory controls, known limits and an owner. Use when the same design questions keep recurring, when reviewers need a baseline to judge conformance, or when a new pattern has been proven and should be reused.

environment-topology draft Mobilise, Deliver, Scale Designs the technical topology a set of AI solutions runs across - Microsoft 365 tenant settings, Power Platform environments, Azure subscriptions and resource groups, regions and the paths between them - so production is separated and data stays within agreed boundaries. Use when the first pro-code or multi-environment AI solution is planned, when Azure and Power Platform estates grow apart, or when data residency affects placement.

grounding-patterns draft Envision, Deliver, Improve Chooses how an AI solution grounds on organisational data - Microsoft 365 work context, curated SharePoint knowledge, Graph connectors, Dataverse or structured data, or a custom retrieval index - judged on permissions, freshness, data movement and ownership. Use when a solution's knowledge spans several stores, when content would be copied or indexed outside its source, or when teams build overlapping indexes of the same data.

platform-selection draft Envision, Deliver, Improve Selects the Microsoft platform for one solution once suitability is agreed - Agent Builder, Copilot Studio, Power Platform automation, Copilot Code or Microsoft Foundry - weighing audience, data, actions, identity, operability and skills, and records the choice in an architecture decision record. Use when a solution has a pattern but no platform, when makers and engineers disagree where to build, or when a build has outgrown its platform.

Skill	Status	Lifecycle	Description
`ai-identity-design`	draft	Deliver, Assure, Improve	Designs the identities an AI solution uses end to end - signed-in users, agent identities, service principals and managed identities - mapping which identity each hop runs under, how consent, scopes and conditional access apply, and who owns each non-human identity. Use when an agent or AI solution calls systems on someone's behalf, when an agent needs its own identity, or when nobody can say whose rights a solution acts with.
`ai-integration-patterns`	draft	Deliver, Assure, Improve	Chooses how an AI solution connects to business systems - standard or custom connectors, flows as actions, APIs, MCP servers, events, Dataverse or Graph - deciding direction, identity, synchronous or asynchronous timing, write confirmation and failure behaviour for each interface. Use when an agent or AI solution must read from or act in other systems, when an interface list is growing unplanned, or when a write action needs a safe pattern.
`ai-non-functional-requirements`	draft	Envision, Deliver, Assure	Specifies the non-functional requirements of an AI solution - quality thresholds, latency, availability, capacity, cost per use, resilience, observability, security, retention, accessibility and supportability - scaled to the risk tier, each measurable with an owner. Use when a solution moves from idea to design, when a pilot is about to become a service, or when nobody can say how good, fast or available the solution must be.
`ai-reference-architecture`	draft	Mobilise, Deliver, Scale, Improve	Maintains a small set of reference architectures for recurring Microsoft AI patterns - knowledge agent, business-data agent with actions, AI-assisted automation, custom Foundry solution - each with components, identity and data flows, mandatory controls, known limits and an owner. Use when the same design questions keep recurring, when reviewers need a baseline to judge conformance, or when a new pattern has been proven and should be reused.
`environment-topology`	draft	Mobilise, Deliver, Scale	Designs the technical topology a set of AI solutions runs across - Microsoft 365 tenant settings, Power Platform environments, Azure subscriptions and resource groups, regions and the paths between them - so production is separated and data stays within agreed boundaries. Use when the first pro-code or multi-environment AI solution is planned, when Azure and Power Platform estates grow apart, or when data residency affects placement.
`grounding-patterns`	draft	Envision, Deliver, Improve	Chooses how an AI solution grounds on organisational data - Microsoft 365 work context, curated SharePoint knowledge, Graph connectors, Dataverse or structured data, or a custom retrieval index - judged on permissions, freshness, data movement and ownership. Use when a solution's knowledge spans several stores, when content would be copied or indexed outside its source, or when teams build overlapping indexes of the same data.
`platform-selection`	draft	Envision, Deliver, Improve	Selects the Microsoft platform for one solution once suitability is agreed - Agent Builder, Copilot Studio, Power Platform automation, Copilot Code or Microsoft Foundry - weighing audience, data, actions, identity, operability and skills, and records the choice in an architecture decision record. Use when a solution has a pattern but no platform, when makers and engineers disagree where to build, or when a build has outgrown its platform.

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.