BuildingIntelligent Enterprises
All product features, frameworks & technical concepts described herein
are the intellectual property of Microsoft Corporation.
This is an independent educational publication. Not affiliated with
or endorsed by Microsoft. GovernGlobal is fictional.
Independent narrative structure: CC BY 4.0
CAST The GovernGlobal Team
GovernGlobal is an enterprise professional services and healthcare consulting firm operating across 14 countries. They advise governments, hospitals, and large enterprises on digital transformation. Patient health records, legal contracts, procurement workflows, and citizen services flow through their systems daily — making compliance, security, and governance non-negotiable from day one. These nine people will design every agent, debate every architecture, and own every outcome.
Bingo
Anir
Abi
Supra
Leon
Sud
NanaJee
Deeno
Gogol
0.1 The Problem Worth Solving
GovernGlobal's daily operations span 14 countries. Their engagement managers manually summarize client meetings into CRM records. Their accounts payable teams match bank statements row by row in spreadsheets. Their procurement analysts review hundreds of contracts each month without AI assistance. Their field engineers arrive on-site at hospitals with no real-time access to the AI-powered guidance that could help them diagnose equipment faults faster.
None of this is unusual. It is the operational condition of most large professional services firms. What makes GovernGlobal different is that they have decided to change it — systematically, with architecture, not experiments.
The question is not whether AI will transform how we work. The question is whether we build the foundation properly before we build the agents on top of it.
0.2 What an AI Agent Actually Is
The word "agent" is used imprecisely in most organizations. Before GovernGlobal builds anything, Anir draws a definition on the whiteboard that the whole team agrees to use.
0.3 The Five Capability Domains
GovernGlobal's AI transformation is organized into five capability domains. Each one is a structural layer — and like floors in a building, you cannot safely occupy the upper floors without the lower ones being architecturally sound. These five domains form the structure of this book.
0.4 The Central Tension of the Whole Program
Before the first line of agent configuration is written, GovernGlobal's team has a tension that every AI program has. It is productive. It is never fully resolved. The book is about how the team manages it.
⚡ Leon wants to ship
- Prototype in three days, deployed in a week
- Learns from production — iteration beats planning
- Technical debt is a future problem
- Real value requires real users
🏗 Anir wants it right
- Architecture decisions compound — wrong now costs 10x later
- GovernGlobal handles patient data — mistakes have legal consequences
- Technical debt in AI isn't just code debt — it's compliance debt
- The second agent is always easier if the first was done properly
Both are right. The book shows how GovernGlobal resolves this tension — not by choosing one or the other, but by building the governance structure that lets Leon ship fast inside boundaries that Anir trusts.
Building a Program That Survives Reality
1.1 The Cloud Adoption Framework — A Sequencing Model
The Cloud Adoption Framework for Azure is Microsoft's prescribed methodology1 for moving workloads and building AI capabilities in the cloud. It is not a checklist — it is a sequencing model. Each phase produces outputs that are the inputs of the next. Skipping phases doesn't eliminate the work; it moves it to production where it costs ten times more to fix.
1.2 The Center of Excellence — Three Shapes, Three Stages
A Center of Excellence is not a team. It is a function that changes shape as organizational AI maturity grows. The danger is keeping the same shape past its useful life. A CoE that doesn't evolve becomes the bottleneck it was created to prevent.
GovernGlobal's legal division built a shadow AI tool using a free-tier subscription because the CoE queue had a seven-week wait time. The tool accessed client contract data with no sensitivity labels, no audit trail, and no governance. That is what happens when a centralized CoE stays Stage 1 too long.
1.3 Use Case Prioritization — The Four-Dimension Filter
GovernGlobal receives 11 AI project proposals in the first planning cycle. Bingo wants to approve all of them. Abi draws a 2×2 grid on the whiteboard and asks each team to score their proposal on four dimensions. By the end of the session, three proposals are in the first delivery wave. Eight are deferred — not rejected, deferred.
1.4 ROAI — Building the Financial Case Properly
Traditional ROI asks: how much did we spend and how much did we save? ROAI asks a harder question: how much did we invest across the full lifecycle — including the costs we haven't paid yet — and what is the realistic range of outcomes given our actual adoption conditions?
1.5 Who Measures What — The Adoption Measurement Architecture
| Role | What They Measure | Tool / Mechanism | Key Metric |
|---|---|---|---|
| Bingo Head of AI | Program credibility; executive-level adoption proof | Copilot Studio usage estimator; Business Value Toolkit | Resolved vs abandoned sessions; adoption rate month-over-month |
| Abi Engagement Mgr | Delivery sequence; stakeholder sign-off cycle | Project tracking; CAF milestone validation | Delivery velocity; blocker resolution time |
| Supra Compliance | Sensitive data access events per agent run | Microsoft Purview audit logs | Sensitive data volume per user per run; anomaly flags |
| Gogol ITSM | AI-attributable incidents; SLA adherence | ITSM platform; automated AI incident tagging | Incident rate per 1,000 sessions; mean time to resolve |
What the Agent Knows and Who Controls It
2.1 Grounding — The Mechanism That Makes AI Trustworthy
Without grounding, an AI agent speaks from its training data — which is vast, general, and impossible to audit. With grounding, the agent speaks from your organization's specific data — which is controlled, attributable, and governable. The grounding architecture is the most consequential design decision in any enterprise AI deployment.
2.2 Microsoft Dataverse — The Enterprise AI Fabric
Dataverse is not a database with a connector attached4 to it4. It is Microsoft's unified data platform designed from the ground up to serve AI agents, Dynamics 365 apps, Power Apps, and external models simultaneously from a single, governed source of truth. The distinction matters because it changes which design decisions you make.
| Need | Dataverse | Azure Data Lake | Cosmos DB | Azure SQL |
|---|---|---|---|---|
| Native AI agent connectivity | First-class | Needs extras | Custom dev | Via connector |
| Built-in classification | ✓ Native AIP | Requires Purview add-on | Custom | External tooling |
| Row-level security | Native — data layer | File-level only | Complex | Yes (schema design) |
| Schema enforcement | Typed, validated | Schema-on-read | Schemaless | Full relational |
| Best for AI grounding | Central SSOT, multiple AI consumers | Raw lake storage at scale | High-throughput transactional | Relational transactional |
Supra's rule: no AI agent goes near patient data without sensitivity labels applied in Dataverse first. Labels are not metadata — they are enforcement mechanisms. The agent can only retrieve what the label permits the calling user to see. Without them, access is unbounded.
2.3 Azure AI Search — When Knowledge Is Distributed
GovernGlobal's knowledge base is not in one system. Policy documents live in SharePoint. Contract data lives in an SQL database. Case management records come from an API. Archived project files are PDFs in blob storage. Azure AI Search solves the heterogeneous data problem by ingesting all source types through configurable indexers and creating one unified semantic index that agents can query.
2.4 Data Residency — Governing 14 Countries
GovernGlobal's EU practice stores patient data in Azure Germany.7 Their Southeast Asia practice stores contracts in Azure Singapore. Their AI services run on Azure models that may be deployed in different regions. Cross-region data movement — sending data from one Azure region to another for AI processing — is not assumed. It must be explicitly governed.
2.5 Power BI Semantic Models as AI Sources
GovernGlobal's finance team has spent three years building a certified Power BI semantic model representing client revenue, project margins, and resource allocation — validated by audit, trusted by CFOs across 14 countries. This model should serve as the grounding layer for Bingo's executive briefing agent. But there is a right way and three wrong ways to expose it.
Endorse the Semantic Model6
Registers the model in the AI-ready catalog. Preserves live DirectQuery connectivity. Inherits existing row-level security. The executive agent sees current data with the CFO's access controls intact.
Export to CSV
Creates a static snapshot. Loses live connectivity. Loses row-level security. Executive queries yesterday's data as if it were today's. Compliance risk.
Copy to Dataverse
Creates a raw copy with no DAX measures, no dimensional hierarchies, no business logic. The AI gets numbers without meaning.
Share the Workspace
Makes the workspace visible to additional users. Does not register the model as an AI grounding source. Agent cannot query it.
Designing Agents That Don't Surprise You
3.1 The Copilot Studio Ceiling — Know It Before You Design8
Deeno's first question at every architecture review: "Can Studio solve this?" His second question, which most teams never ask: "What happens when it can't?" Understanding the platform ceiling is not pessimism — it is the design discipline that prevents six-week rework when a requirement turns out to exceed the platform's capability.
3.2 Language Models — Three Contracts, Not Three Quality Tiers
Selecting a language model is not about picking the "most capable" option. It is about matching the interaction contract to the business requirement. Each model type provides a different guarantee — and that guarantee is the design decision, not a performance consideration.
A generative NLU model at temperature zero is not deterministic. It is "approximately consistent." That is not the same thing. When a HIPAA auditor asks us to reproduce a specific patient eligibility response for a compliance review, "approximately consistent" is not an acceptable answer. We use NLU with authored dialog nodes for eligibility. Full stop.9
3.3 Orchestration Models — Two Routing Philosophies
Classic Orchestration
- Trigger phrases route to specific topics — hardcoded matching
- Same input always routes to same topic — fully predictable
- New topics require new trigger phrase sets to be defined
- Cannot dynamically discover or route to other agents
- Debug easily: trace which phrase triggered which topic
Generative Orchestration
25- Topics activated by description of their purpose — no triggers needed
- New agents auto-discovered based on capability description
- Routes to other agents dynamically — enables multi-agent composition
- Handles varied phrasing naturally without exhaustive trigger lists
- Required when: "topics selected based on description, not trigger phrase"
3.4 Topic Architecture — The Three Safety Exits
3.5 Computer Use10 & MCP — Two Different Keys to Locked Rooms
Computer Use in Copilot Studio10
The problem it solves: GovernGlobal's government practice submits documents to a legacy benefits portal with no API. The only interface is a web form.
How it works: The AI model evaluates the page layout at runtime — not at design time. When the government portal updates its UI (which it does quarterly without notice), Computer Use re-identifies elements by context and purpose. The automation survives the update.
Use when: no API exists or UI changes frequently
Model Context Protocol (MCP)
The problem it solves: GovernGlobal's legal team updates their jurisdiction compliance rules weekly. The AI agent needs these updates — but requiring the AI team to update the agent each time is unsustainable.
How it works: An MCP server exposes the legal team's tools through a standardized protocol.11 At runtime, the agent queries the MCP server to discover what tools are currently available, then invokes them. New tools added by the legal team are immediately available to the agent — no redeployment.
Use when: tool catalog changes or is owned by another team
3.6 Multi-Agent Architecture — Earn the Complexity
Abi proposes a seven-agent architecture for GovernGlobal's government practice. Anir draws it on the whiteboard, then asks: "Which of these agents cannot be a topic in a single agent?" The answer is two. The seven-agent proposal becomes a two-agent architecture. Both requirements are met. The debugging surface is 70% smaller.
| Signal | Single Agent | Multi-Agent |
|---|---|---|
| Security boundary | All tasks use data the agent can uniformly access | Tasks cross security boundaries — patient data vs operational data requires separate permission scopes |
| Specialization value | General agent handles 80%+ of scenarios at acceptable quality | Specialized agents demonstrably outperform a generalist for their specific domain |
| Team maturity | Team is new to AI agent development | Team has successfully operated single-agent systems in production |
| Anir's rule | Start with the minimum agent count that delivers core value. Add agents only when a single agent demonstrably fails to meet a specific requirement. | |
The Right Copilot for the Right Role
4.1 The First Question: Does It Already Exist?
Deeno is designing a Copilot Studio agent with Exchange connectors for email assistance when Abi stops him. "Does this already exist in D365 Sales?" It does — Copilot email assist ships with the product12. Deeno was about to spend three weeks building something Microsoft already built. Abi's rule applies before any build decision is made.
4.2 13Copilot for Sales — Three Surfaces, Three Use Cases
4.3 Field Service — Two Users, Two Copilots
GovernGlobal's healthcare equipment maintenance practice has dispatchers who coordinate field engineers from an office (Outlook + Teams), and field engineers who visit hospitals to service medical equipment on site (Field Service mobile app)14. Same organization. Two different users. Two completely different Copilot integrations.
📧 Copilot in Outlook — For Dispatchers
- Drafts service assignment communications
- Summarizes correspondence threads from engineers and clients
- Prioritizes work orders by urgency and location
- User: Back-office dispatcher with full screen access
📱 Copilot in Field Service — For Engineers
- Work-order summaries on mobile app before arriving on site
- Suggested resolution steps based on fault code
- Relevant knowledge articles for the specific equipment model
- User: Field engineer in a hospital — often hands-full, no desk access
4.4 Finance Copilot — Three Distinct Capabilities
| Capability | What It Does | GovernGlobal Use Case | Prerequisite |
|---|---|---|---|
| Account Reconciliation Agent | Automates matching of bank statements to vendor ledger and invoice records. Surfaces overdue invoices and outstanding balances. | AP team processes vendor invoices across 14 countries — 3 hours/day of manual statement matching eliminated | Finance and Operations AI security role15 assigned |
| Collections Coordinator Summary | Generative AI aggregates payment histories, aging reports, and communication records into a concise narrative per account | Collections managers review 40 accounts/day — summary reduces per-account review from 25 minutes to 4 | Finance and Operations AI security role assigned |
| Finance AI Security Role | Grants permissions to access AP data, invoke AI models, write back results for prebuilt Finance Copilot capabilities | Supra assigns this role in Power Platform admin center before any Finance Copilot user can access the capabilities | This IS the prerequisite — must exist first |
4.5 Supply Chain Management Copilot
AI Summaries with Copilot
Analyzes customer order data and generates natural language summaries of trends, purchasing patterns, and anomalies for operations managers. GovernGlobal's procurement directors receive a daily briefing paragraph instead of a Power BI dashboard to manually interpret.
Generative Insights for Demand Planning
AI-powered demand forecasts based on historical sales patterns, seasonal signals, and current order velocity. GovernGlobal's planners build 90-day procurement forecasts with AI augmentation — reducing planning cycle time and improving forecast accuracy.
Agent Management16
GovernGlobal's supply chain CTO wants to evaluate which prebuilt AI agents are available before committing to deployment. Agent Management in D365 SCM is the discovery catalog — descriptions, use cases, estimated value, and capability previews. This is where you go before Copilot Studio.
4.6 Contact Center — The Live Agent Hand-Off Architecture
GovernGlobal's citizen services practice runs a contact center for a government client. Citizens call with benefits questions. Most are routine. Some are distressed. The agent must be able to help the first group and safely hand off the second. The hand-off architecture is not optional — it is the safety mechanism.
Citizen calls — NLU+ handles voice channel
GovernGlobal's Contact Center agent uses NLU+ — required for voice channel integration with D365 Contact Center.24 Enhanced context awareness ensures multi-turn benefits conversations are handled correctly.
Agent handles routine queries from indexed knowledge
Eligibility questions, document requirements, appointment scheduling — all handled by authored topics with deterministic responses. Supra has approved every authored response.
Escalation trigger: "I want to speak to someone"
The Escalation Topic detects the intent. It ends the bot session. It invokes the built-in hand-off action — passing the full conversation transcript, citizen case number, query category, and session ID to the routing layer.
Customer Engagement Hub routes to correct queue17
The Hub receives the escalation with full context. It routes to the appropriate agent queue based on query category and citizen language preference. The live agent sees the complete transcript before saying hello.
Gogol's ITSM record is created automatically
Every escalation generates an ITSM ticket: escalation reason, session ID, citizen identifier (masked), timestamp, queue route. If the bot's escalation rate spikes, Gogol sees it in his dashboard before anyone else knows. That is the operational governance loop closed.
The Architecture Nobody Sees Until It Fails
5.1 Managed vs Unmanaged — The Deployment Contract18
The incident that starts this chapter: a developer found a bug in a live agent, fixed it directly in the production environment because it was deployed as an unmanaged solution18, and did not create a change record. Three days later, Supra's Purview alert fires — the modified component had accessed a Dataverse table containing patient health records. There is no audit trail for the modification. This is what unmanaged solutions in production environments enable.
5.2 Microsoft Purview — GovernGlobal's AI Oversight Command Center20
Purview is not one tool for one requirement. For GovernGlobal's AI program, it serves three distinct functions — each owned by a different role, each solving a different governance problem.
5.3 Responsible AI — Six Principles as Architectural Requirements
Microsoft's Responsible AI framework defines six principles21. GovernGlobal's mistake in month three is treating them as a values statement to be completed at the deployment gate. Anir's correction: these are technical requirements with specific architectural implementations. Discovering them post-development creates expensive rework. The Microsoft Cloud Adoption Framework's responsible innovation guidance26 reinforces this design-time approach.
5.4 Prompt Engineering as Governed Practice
| Problem | What Goes Wrong in Production | Correct Design |
|---|---|---|
| Vague instruction "Help the customer as best you can" | High-variance outputs. Some interactions work. Some don't. Variance is invisible until a high-stakes interaction fails. | Clear task-specific instruction: the task, constraints, scope, and format. Explicitly. |
| No source constraints General knowledge enabled | Agent blends validated internal policy with training-data general knowledge. Answers sound authoritative. Cannot be attributed. Compliance incident waiting. | Restrict to indexed reference sources only. Disable general model knowledge for compliance-sensitive agents. |
| Identical-phrasing test inputs | Agent passes testing but fails when real users phrase questions the way real users do — colloquial, incomplete, ambiguous. | Test with varied phrasing: synonyms, informal expressions, partial sentences, different languages. Cover the real input distribution. |
| Wrong quality metrics Generation time, word count | Team optimizes for speed and brevity. Whether the AI actually helped is never measured. | Primary: response relevance + accuracy. Secondary: consistency. Generation time is performance. Word count is formatting. Neither measures value. |
5.5 The Full GovernGlobal Architecture — What Was Built
At the end of this program, GovernGlobal has not just deployed agents. They have built a compounding system — one where the governance infrastructure strengthens every agent added to it, rather than one that accumulates technical and compliance debt with each deployment.
We did not build a technology project. We built an architecture. Technology projects end when the last agent is deployed. Architectures compound — every agent we add now is safer, faster to build, and easier to govern than the one before it. That is what the foundation work buys.
What GovernGlobal Uses, Where, and Why
6.1 Anir's Rule: Tool Choice Follows the Scenario
GovernGlobal stops asking "Which AI tool should we use?" Anir changes the question: "What decision does this scenario influence, what data does it touch, what action can it take, and what evidence must exist before production?" The platform decision follows from risk, data, integration and operating requirements — not from excitement about a capability.
Deeno writes six decision rules on the whiteboard. These become GovernGlobal's standing pattern for every new AI request.
Check native capability first — Deeno
If Dynamics 365 or Microsoft 365 already provides the required Copilot capability, configure the native feature before building a custom agent. Reduces maintenance, security and ALM overhead.
Use Copilot Studio for bounded conversational agents — Sud and Leon
Use Copilot Studio when the requirement is a low-code agent with instructions, topics, supported knowledge sources, tools, triggers, channels and testable conversation flows.
Use Dataverse for governed business records — Supra
Use Dataverse where the agent needs structured records, business tables, security roles, auditable data changes and integration with Power Platform or Dynamics 365.
Use Azure AI Search for distributed enterprise content — Anir
Use Azure AI Search where the solution needs custom indexing, hybrid or vector retrieval, semantic ranking, enrichment or retrieval pipelines outside Copilot Studio's built-in knowledge-source limits.
Use Power Automate, connectors and APIs for actions — NanaJee
Use supported connectors or Power Automate flows for controlled actions. Use API Management or custom APIs where enterprise APIs need authentication, throttling, logging and policy control. Every endpoint registered before any agent can call it.
Use Azure AI Foundry for high-control AI engineering — Anir
Use Azure AI Foundry where the scenario needs custom model orchestration, formal evaluation, monitoring, tracing, prompt and model lifecycle management, or deeper engineering control beyond low-code configuration.
6.2 Scenario-to-Tool Map
The same GovernGlobal use cases from Modules 1–5 now have implementable platform choices. Each row states the preferred toolset, when to use it, what to avoid, and what evidence must exist before go-live.
| Scenario | Recommended Tooling | Use When | Avoid / Important Note | Go-live Evidence |
|---|---|---|---|---|
| IT Helpdesk Agent Low risk · Wave 1 |
Copilot Studio, Teams channel, SharePoint knowledge source, Power Automate → ITSM, Power Platform DLP, Copilot Studio analytics | Internal support Q&A, service request triage, KB search, ticket creation, human escalation | Do not allow privileged actions — password reset, device isolation, group changes or script execution — without a separate approval path | Approved KB source list, fallback topic, escalation topic, ITSM ticket test, DLP policy, usage and unresolved-session metrics |
| Procurement Contract Review Medium risk · Wave 2 |
Copilot Studio, SharePoint or Dataverse knowledge where sufficient, Azure AI Search where custom indexing is required, Power Automate approval, Purview sensitivity labels | Contract clause search, policy comparison, supplier metadata lookup, review summary with cited sources | Do not present AI output as legal advice. Do not allow ungrounded answers for contractual interpretation. Human review required for high-risk clauses. | Data classification, source permission test, citation samples, ungrounded-answer setting reviewed, approval workflow, audit sample |
| Patient Intake / Eligibility High risk · Wave 3 |
Copilot Studio authored topics, validated intake questions, Dataverse records, D365 Contact Center or Customer Service escalation where applicable, Entra ID, Purview audit | Administrative intake, appointment routing, collection of non-emergency information, controlled eligibility pre-check where the final decision remains human-owned | Microsoft documentation is explicit: Copilot Studio is not a medical device and must not be used for emergencies, medical advice, diagnosis or treatment. Emergency pathway must be designed separately. | Clinical or legal review of wording, emergency disclaimer, escalation path, deterministic topic tests, access controls, audit trail, human review path |
| D365 Sales Assistance Native first · Wave 2 |
Copilot in Dynamics 365 Sales and Microsoft 365 Copilot for Sales where licensed and enabled | Email assistance, opportunity summaries, CRM-context sales preparation, Outlook and Teams sales workflows | Do not rebuild native D365 Sales Copilot in Copilot Studio unless native configuration cannot meet the requirement. Abi's first question: does it already exist? | Security-role review, feature availability check, data access validation, adoption metrics, user training |
| Field Service Guidance Native first · Wave 2 |
Dynamics 365 Field Service Copilot capabilities, Field Service mobile app, work-order data, knowledge articles | Technician work-order summaries, service history, knowledge articles, resolution assistance | Do not solve mobile field-technician workflows with only back-office Copilot experiences. Validate the actual user surface — Copilot in Customer Service does not extend to field mobile workers. | Role access, mobile app test, work-order data quality check, knowledge article ownership, field-pilot feedback |
| Finance Reconciliation High risk · Wave 3 |
Dynamics 365 Finance Copilot capabilities where available, Finance and Operations AI security role, Power BI reporting, Purview audit, approval workflow | Finance summaries, reconciliation assistance, collections preparation and exception review | Do not allow automated financial write-back without segregation of duties and human review. Treat finance AI as decision support unless formally approved otherwise. | Security-role assignment, SoD review, audit trail, exception queue, finance owner sign-off, reconciliation test |
| Contact Centre Escalation Medium-high risk · Wave 3 |
Copilot Studio agent, escalation topic, D365 Contact Center or Customer Service hand-off where applicable, transcript and context transfer, service dashboard | Routine customer or citizen queries with explicit hand-off to live agents for complex or distressed interactions | Do not deploy customer-facing automation without tested escalation, transcript transfer and service-quality monitoring. | Escalation tests, hand-off transcript validation, queue routing test, service owner sign-off, abandoned-session metric |
| Legacy Portal Automation Medium-high risk |
Copilot Studio Computer Use only where an API or connector does not exist, with narrow task scope and human approval for consequential actions | UI automation against legacy web or desktop interfaces that cannot be accessed through supported APIs | Computer Use is not the first option. Prefer APIs and connectors. UI automation can be brittle and action-impact risk is higher. Strong guardrails required. | Allowed screen and action list, test account, rollback path, human approval gate, audit log, exception handling |
| Multi-Jurisdiction Legal AI Very high risk · Wave 4 |
Azure AI Foundry, Azure AI Search, Azure OpenAI where approved, evaluation and monitoring, API Management, legal review workflow | Complex retrieval, jurisdiction-specific knowledge, evaluation-driven quality control, monitored reasoning assistance | Do not use basic low-code Q&A for legal interpretation. Do not present outputs as final legal advice. Require legal owner review and contestability path. | Evaluation results, red-team tests, jurisdiction source register, citations, legal review, risk acceptance, monitoring dashboard |
6.3 Who Owns What — Character Responsibilities
The missing link in most AI guidance is ownership. Principles are easy to write and hard to operationalise. GovernGlobal makes ownership explicit: every principle has a character, every character makes a decision, every decision produces evidence.
| Character | Their Decision | Architecture Principle They Apply | Evidence They Produce |
|---|---|---|---|
| Bingo — Head of AI | Selects use cases, owns business value, accepts executive risk | AI investment must be outcome-led, measurable and linked to real operational value | ROAI baseline, adoption metrics, benefit realisation dashboard, executive risk acceptance |
| Anir — Platform Architect | Chooses platform pattern, integration model, agent boundary and production architecture | Every AI system must be grounded, identity-aware, bounded, observable and designed to fail safely | Architecture Decision Record, data-flow diagram, pattern selection rationale |
| Abi — Engagement Manager | Controls sequencing, stakeholder sign-off, delivery dependencies and adoption readiness | AI delivery must follow gated adoption, not uncontrolled experimentation | Intake register, delivery roadmap, approval log, pilot exit criteria, readiness assessment |
| Supra — Identity & Compliance | Controls identity, sensitivity labels, compliance posture, data access and RAI review | No agent may access data unless classification, access control and audit paths are confirmed | Data classification record, Purview audit evidence, access review, privacy and security assessment |
| Leon — Vibe Coder | Prototypes quickly, validates technical feasibility and proves the user experience | Speed is acceptable only inside approved guardrails | Prototype scope, sandbox boundary, telemetry sample, cost estimate |
| Sud — Developer | Builds agents, flows, connectors, prompts, topics and deployment assets | Prompting, topic logic and connector actions must be versioned and testable | Managed solution export, prompt test cases, deployment notes, rollback plan |
| NanaJee — API & Integration | Controls APIs, MCP servers, endpoint registration, gateway and action boundaries | Agents must use approved integration paths and must not become shadow API clients | Endpoint catalogue, API permission map, MCP tool register, logging evidence |
| Deeno — Power Platform Architect | Decides whether Copilot Studio, D365 native Copilot or custom Azure AI is the right pattern | Configure before building; low-code before custom code; custom only when requirements exceed platform ceiling | Platform-fit assessment, D365 capability check, Copilot Studio ceiling assessment, exception approval |
| Gogol — ITSM Specialist | Owns operational visibility, incidents, change records, service health and support readiness | Every production AI system must produce operational signals and support records | ITSM change record, incident taxonomy, support runbook, escalation trend dashboard |
6.4 Tool Control Matrix
This matrix is the practical bridge from architecture principle to implementation tool. It uses real control planes available in the Microsoft ecosystem — no invented products.
| Tool | What GovernGlobal Uses It For | Key Implementation Note | Owner |
|---|---|---|---|
| Copilot Studio | Low-code agents, topics, instructions, tools, triggers, channels, testing and analytics | Use for bounded conversational agents. Configure knowledge, fallback, escalation and channel deployment explicitly. | Deeno + Sud |
| Supported knowledge sources | Grounding agents in enterprise content | Use SharePoint, documents, Dataverse, websites or connector-based sources depending on source type and authentication requirements. | Anir + Supra |
| Dataverse | Structured records, app data and governed business tables | Use security roles, table design, audit settings and environment governance. Do not treat Dataverse as a dumping ground for unclassified content. | Supra + NanaJee |
| Azure AI Search | Custom retrieval over distributed enterprise data | Use for index design, enrichment, vector and hybrid retrieval, semantic ranking and retrieval patterns needing more control than built-in knowledge sources. | Anir |
| Power Platform DLP23 | Connector governance across Power Apps, Power Automate and Copilot Studio | Classify connectors into appropriate policy groups. Prevent unsafe mixing of business and non-business connectors. | Supra |
| Microsoft Purview | Sensitivity, audit, compliance and AI governance evidence | Use sensitivity labels, audit review and data governance controls. Do not rely on agent design alone for data governance. | Supra |
| Entra ID | Authentication, user identity and access boundaries | Validate whether the agent uses user identity, app identity, delegated access or connector-specific authentication. Review access for sensitive scenarios. | Supra |
| Power Automate | Workflow actions, approvals and ticket creation | Use for repeatable business workflows, human approval and integration steps. Keep high-impact actions behind approvals. | Sud + Gogol |
| API Management / custom APIs | Governed enterprise API exposure | Use where agent actions call enterprise services requiring authentication, throttling, policy, logging and lifecycle ownership. | NanaJee |
| MCP server | Tool exposure to agents where the toolset is external or changes over time | Use only when MCP is required and supported for the agent pattern. Maintain a tool register, owner and allow-list. See the MCP Governance Framework for the five-pillar governance model: architecture, controls, operating model, assurance and Australian AI alignment.27 | NanaJee + Anir |
| Computer Use | UI automation where no API or connector exists | Use narrowly, with test accounts, explicit allowed actions and human approval for consequential steps. Prefer APIs first. | Anir + Gogol |
| Azure AI Foundry | Evaluation, monitoring, tracing, model and prompt lifecycle and high-control AI engineering | Use for complex or high-risk AI systems requiring evaluation pipelines, observability and engineering control beyond low-code agent configuration. | Anir |
| Power BI / Fabric | Adoption, quality, cost, incident and service reporting | Use as reporting layer over operational data, telemetry exports, ITSM data and adoption metrics. | Bingo + Gogol |
| ITSM platform | Operational ownership, incidents, changes and support requests | Every production agent must have an owner, support group, incident category, change process and escalation path. | Gogol |
6.5 Visual Pattern — IT Helpdesk Agent
This is the safest first production pattern: internal, bounded, measurable and easy to escalate. The agent answers from approved support content and creates ITSM tickets. It does not directly remediate endpoints.
6.6 Visual Pattern — Patient Intake
For healthcare-style scenarios, GovernGlobal applies the strictest interpretation: the agent supports administration and routing. It does not diagnose, treat, replace professional judgment or handle emergencies. High-impact decisions stay human-owned.
From Responsible AI Theory to Release Evidence
| Reference page | What the architect learns there | How it is applied in GovernGlobal |
|---|---|---|
| Australia AI Guidance Navigator | Why the AI solution must be governed: ethics principles, AI6-style practices, accountability, transparency, safety and human oversight. | Used in Production Assurance to decide what evidence is needed before an agent goes live: data classification, human escalation, contestability, audit and owner sign-off. |
| AI Architecture Principles | How to design the solution: grounded data, identity-aware access, bounded actions, observability, fallback, ALM and production support. | Used in each GovernGlobal scenario to choose the right pattern: Copilot Studio, Dataverse, Azure AI Search, D365 Copilot, Foundry, MCP or controlled automation. |
| MCP / Agentic AI Guidance Framework | How to control agentic behaviour: tool registration, action boundary, approval, monitoring, incident response and runtime governance. | Used when the agent can call tools, APIs, workflows, MCP servers or legacy UI automation. It defines what the agent is allowed to do and what must be logged. |
7.1 Australia AI and Microsoft Responsible AI — The Mapping
GovernGlobal uses Microsoft implementation tools, but their Australian government client requires alignment to Australia's AI Ethics Principles. The Australia AI Navigator makes this straightforward: the local governance language28 and Microsoft's Responsible AI principles name the same requirements in different words. The Navigator's AI6 Practices and the May 2026 agentic AI guidance (ASD ACSC, CISA, NSA, CCCS, NCSC-NZ, NCSC-UK) add the operational and agentic-specific controls on top.
| Governance Principle | What It Means in Practice | Tool Evidence GovernGlobal Produces | Scenario Where It Applies |
|---|---|---|---|
| Privacy protection and security AU P4 · MS Privacy & Security | The agent only accesses approved data, with clear identity and connector boundaries | Entra access model, Dataverse security role, SharePoint permission test, DLP policy, Purview audit sample | Procurement contract review, patient intake, finance reconciliation |
| Reliability and safety AU P5 · MS Reliability & Safety | The agent fails safely, uses tested flows and escalates when uncertain | Topic test cases, fallback test, escalation test, Azure AI Foundry evaluation where used | Patient intake, contact centre escalation, eligibility pre-check |
| Transparency and explainability AU P6 · MS Transparency | The user knows the source, the limitation and the next step. High-impact outputs need an explanation. | Citation samples, disclosure text, explanation template, response-quality review | Contract review, legal research, finance summaries |
| Contestability AU P7 · MS Accountability | Affected users can challenge or escalate the AI-assisted outcome | Human review queue, ITSM or case record, escalation SLA, owner assignment | Eligibility pre-check, citizen services, finance exceptions |
| Fairness and inclusiveness AU P3 · MS Fairness | The pilot covers realistic users, languages, channels and accessibility needs | Representative test set, pilot feedback, quality comparison by channel and language where available | Contact centre, field service, 14-country internal support |
| Accountability AU P8 · MS Accountability | Every production agent has an owner, a support model, a change record and a review cadence | Named owner in ITSM service catalog, architecture decision record, ITSM change record, monthly service review | All production agents |
7.2 The Five-Gate Release Process
Abi runs the intake. Supra classifies the data. Anir scores the architecture risk. Deeno recommends the platform. Gogol defines the operational support model. Only then does Leon prototype and Sud build. GovernGlobal stops treating AI ideas as tickets to build.
Use case intake — Abi
Business owner, intended users, decision impact, expected value, deployment channel, and whether the agent only informs, recommends or acts. Recorded in ITSM before any build begins.
Data and identity review — Supra
Data classification, source permissions, authentication model, DLP policy and sensitivity and audit needs. Supra signs. No agent accesses data until this gate is closed.
Architecture pattern decision — Anir
Confirms whether the pattern is native D365 Copilot, Copilot Studio, custom retrieval with Azure AI Search, Computer Use, MCP, or Azure AI Foundry. Records the ADR with reasons for selection and rejection. Deeno validates the platform fit.
Build and test evidence — Sud and Leon
Topics, fallback, escalation, prompt and response samples, retrieval and citation tests, workflow action tests, evaluation results where applicable. 200-case prompt pipeline from Module 5 runs here.
Operate and review — Gogol
Support group, incident category, change process, service dashboard and review cadence confirmed before go-live. ITSM change record created. Rollback plan documented.
7.3 Risk Tiers and Minimum Evidence
GovernGlobal does not apply the same release gate to every agent. Risk determines evidence depth. A helpdesk Q&A agent does not need the same review as a healthcare or legal assistant — but it still needs a support model, approved sources and a fallback path.
| Risk Tier | Example Scenarios | Minimum Evidence Required | Additional for This Tier |
|---|---|---|---|
| Low Wave 1 |
Internal helpdesk Q&A, internal policy FAQ | Approved KB source list, fallback topic, escalation topic, DLP policy, ITSM ticket test, support owner named | Monthly analytics review |
| Medium Wave 2 |
Procurement contract review, D365 Sales assistance, Field Service guidance | Data classification, citation testing, source permission test, role-based access review, approval workflow, audit sample | Legal or procurement owner sign-off for high-risk clause categories; adoption training |
| High Wave 3 |
Patient intake, Finance reconciliation, Contact Centre escalation, citizen service triage | Human escalation tested, deterministic authored logic for high-impact decisions, privacy and security review, service quality monitoring dashboard active | Fairness and inclusion test set, incident playbook, formal owner risk acceptance, Purview audit evidence |
| Very high Wave 4 |
Multi-jurisdiction legal AI, cross-region clinical guidance, automated contract legality analysis | All high-risk controls plus: Azure AI Foundry evaluation, red-team testing, legal review, contestability workflow | Executive risk acceptance, post-go-live formal review, jurisdiction source register, legal owner named on every output |
7.4 Deployment Waves — Same Story, Now With Gates
GovernGlobal does not start with patient eligibility or multi-jurisdiction legal reasoning. It starts with bounded, measurable, recoverable scenarios and only scales after governance muscle is working. Wave order is not negotiable.
7.5 Architecture Decision Record
Every agent now has a short Architecture Decision Record. It captures not only what was chosen, but what was rejected and why. Anir's rule: if you cannot explain why you did not use the simpler option, you have not justified the complex one.
ADR Template — GovernGlobal AI Agent Decision
| Field | What to Record |
|---|---|
| Use case | Name of the agent and the business problem it solves |
| Business owner | Named accountable person — not a team mailbox |
| Users and channels | Teams, web, mobile, D365, contact centre or other approved channel |
| Data sources | SharePoint, Dataverse, Dynamics 365, Azure AI Search index, API, file source or other approved source |
| Authentication model | User identity, app identity, connector auth, delegated access or service principal |
| Selected platform | Native D365 Copilot, Copilot Studio, Azure AI Search, Azure AI Foundry, Computer Use, MCP, or custom integration |
| Rejected options | State why a simpler or native option was not sufficient |
| Actions allowed | Inform only, recommend, create ticket, submit approval, update record or call API |
| Actions blocked | Explicitly state what the agent must not do |
| Responsible AI controls | Fairness, reliability/safety, privacy/security, inclusiveness, transparency and accountability evidence |
| Go-live evidence | Test results, approvals, monitoring setup, support model, rollback path and first review date |
7.6 Production Operating View
GovernGlobal's production view is not a new product. It is a combined view built from real control planes. Gogol assembles it. Bingo reads it quarterly. Supra checks it monthly for security signals.
7.7 Production Readiness Checklist
The final gate requires evidence, not optimism. If an item cannot be proven in a system record or test result, the agent is not production-ready. Gogol owns this list. Nothing goes live until every item has an answer.
| # | Gate Item | What It Means |
|---|---|---|
| 1 | Owner named | Business owner, architecture owner, data owner and support owner are documented in ITSM |
| 2 | Tool decision recorded | ADR explains why the chosen platform was selected and why simpler or native options were not sufficient |
| 3 | Data classified | Sources, sensitivity labels, access model, residency and retention are documented and Supra has signed off |
| 4 | Grounding tested | Knowledge sources, citations, retrieval quality and fallback behaviour are tested with evidence attached |
| 5 | Actions constrained | Allowed and blocked actions are explicit. High-impact actions have approval gates or mandatory human review. |
| 6 | DLP applied | Connector policy has been reviewed so business data is not mixed with inappropriate connector categories |
| 7 | RAI evidence complete | Fairness, reliability, safety, privacy, transparency, inclusiveness and accountability have test or review evidence attached |
| 8 | Escalation works | Fallback, live hand-off, ITSM ticketing or case routing has been tested end-to-end |
| 9 | Monitoring exists | Usage, failures, escalations, unresolved sessions, cost and quality signals have a named owner and a review cadence |
| 10 | Change path defined | Development, test and production deployment plus rollback follow a managed solution or approved change process |
A tool choice is not an architecture. The architecture is the tool choice plus the data boundary, the action boundary, the evidence pack, the operating model and the accountable owner. When all five exist, the agent is ready to go live. Not before.
& Legal Notices
§1 Copyright, Ownership & Intended Use
What this book actually is
This publication is an independent educational commentary on Microsoft's Agentic AI product stack — Copilot Studio, Dynamics 365 AI features, Power Platform, Azure AI services, Microsoft Purview, and related frameworks. It was written to help architects, developers, and practitioners understand these products in a structured, narrative-driven way.
Every technical concept, feature name, framework, and capability described in this book is Microsoft's intellectual property. The Cloud Adoption Framework, Copilot Studio, Dataverse, Azure AI Search, NLU/NLU+ models, Computer Use, MCP integration, D365 Copilot features, ALM Accelerator19, Microsoft Purview, Responsible AI principles — all of it belongs to Microsoft. This book explains those concepts; it does not own them.
What is original here — and only this — is the fictional GovernGlobal narrative, the nine fictional characters, the specific teaching structure and chapter arrangement, and the original explanatory prose written to contextualise Microsoft's products. Those elements are the authors' original creative work and are released under CC BY 4.0.
⚠ For Reading & Guidance Purposes Only
This publication is intended for educational reading and general guidance only. It is not:
- Official Microsoft documentation — always defer to learn.microsoft.com for authoritative, current feature documentation
- Legal, compliance, or regulatory advice — HIPAA, GDPR, and other regulatory references are illustrative only
- Microsoft-endorsed or Microsoft-affiliated — this is an independent publication with no relationship to Microsoft Corporation
- A substitute for professional architectural review — decisions based on this material should be validated by qualified architects against your organisation's specific requirements and current Microsoft documentation
- A guarantee of accuracy — Microsoft products, features, pricing, and URLs change continuously. Content was accurate at time of writing (2025) but may be outdated by the time you read it
Licence for original elements only (the narrative, characters, and teaching structure): Creative Commons Attribution 4.0 International (CC BY 4.0). Free to share, adapt, and build upon with attribution: "Building Intelligent Enterprises — The GovernGlobal Story, Govern Global Practice, 2025."
creativecommons.org/licenses/by/4.0 — This licence applies only to the original creative elements, not to any Microsoft IP referenced within.
§2 Fictional Company Disclaimer
GovernGlobal is entirely fictional
GovernGlobal, and all characters associated with it — Bingo, Anir, Abi, Supra, Leon, Sud, NanaJee, Deeno, and Gogol — are entirely fictional. They were created exclusively for educational purposes to illustrate architectural concepts, decision-making processes, and real-world design tensions that arise in enterprise AI programs.
Any resemblance to any real company, organisation, or individual — living or deceased — is entirely coincidental and unintended.
No real patient health records, client contracts, procurement data, or citizen information of any kind are represented in this publication. All scenarios are hypothetical constructs designed to teach architectural principles.
HIPAA, GDPR, and other regulatory references appear for illustrative purposes to contextualise why specific architectural decisions matter in regulated industries. This document does not constitute legal, compliance, or regulatory advice. Organisations must obtain appropriate professional advice for their specific compliance obligations.
§3 Microsoft Trademark Attributions
The following names, product names, and feature names are trademarks or registered trademarks of Microsoft Corporation. Their use in this educational publication is for descriptive and referential purposes only, consistent with nominative fair use. Govern Global Practice makes no claim to ownership of any of these marks.
All other trademarks mentioned in this document are the property of their respective owners. The appearance of a trademark in this document does not constitute endorsement by or affiliation with the trademark owner.
§4 References & Source Citations
All references below are to publicly available, freely accessible Microsoft documentation hosted at learn.microsoft.com, microsoft.com, and azure.microsoft.com. No paywalled, proprietary, or third-party sources have been used as the factual basis for content in this book.
-
1Microsoft Cloud Adoption Framework for AzureStrategy · MethodologyThe end-to-end Microsoft-endorsed methodology for cloud and AI adoption: strategy, planning, readiness, migration, and governance phases.
learn.microsoft.com/azure/cloud-adoption-framework/ -
2Power Platform Business Value ToolkitROI · MeasurementMicrosoft's official tool for mapping Power Platform AI investments to measurable business outcomes using metadata and telemetry.
learn.microsoft.com/power-platform/guidance/adoption/business-value-toolkit -
3Azure Total Cost of Ownership (TCO) CalculatorCost Modelling · Pre-deploymentPre-deployment cost modelling tool for Azure workloads. Produces exportable business-case-ready cost estimates across compute, storage, AI services, and networking.
azure.microsoft.com/pricing/tco/calculator/ -
4Microsoft Dataverse OverviewData Platform · Power PlatformIntroduction to Microsoft Dataverse — the unified data platform for Power Platform, Dynamics 365, and external AI integrations.
learn.microsoft.com/power-apps/maker/data-platform/data-platform-intro -
5Azure AI Search — Indexer ConceptsKnowledge Architecture · SearchDocumentation covering Azure AI Search indexers, incremental indexing, change detection policies, and multi-source knowledge aggregation.
learn.microsoft.com/azure/search/search-indexer-overview -
6Endorse Your Content in Power BIPower BI · AI GroundingMicrosoft documentation on promoting and endorsing Power BI semantic models to register them as AI-ready, trusted data sources.
learn.microsoft.com/power-bi/collaborate-share/service-endorsement-overview -
7Power Platform — Data Residency and RegionsGovernance · Data ResidencyDocumentation covering Power Platform environment regions, cross-region data movement configuration, and data residency compliance.
learn.microsoft.com/power-platform/admin/regions-overview -
8Microsoft Copilot Studio — Overview and Key ConceptsAgent Platform · Low-codeFoundational documentation for Microsoft Copilot Studio: what it is, its architecture, capabilities, and integration patterns.
learn.microsoft.com/microsoft-copilot-studio/fundamentals-what-is-copilot-studio -
9Copilot Studio — Natural Language Understanding and Generative AINLU Models · OrchestrationDocumentation covering NLU, NLU+, generative NLU model selection, orchestration modes, and intent recognition in Copilot Studio.
learn.microsoft.com/microsoft-copilot-studio/nlu-boost-conversations -
10Use Computer Use in Microsoft Copilot StudioAgent Capabilities · UI AutomationDocumentation for the Computer Use capability in Copilot Studio — enabling agents to interact with graphical user interfaces of third-party applications.
learn.microsoft.com/microsoft-copilot-studio/computer-use -
11Extend Your Agent Using Model Context Protocol (MCP)Agent Integration · Runtime ToolsDocumentation for connecting Copilot Studio agents to MCP servers for dynamic runtime tool discovery without agent redeployment.
learn.microsoft.com/microsoft-copilot-studio/agent-extend-action-mcp -
12Copilot in Dynamics 365 Sales — OverviewD365 Sales · Copilot FeaturesOverview of Copilot capabilities in Dynamics 365 Sales, including email assist, opportunity summaries, and meeting preparation features.
learn.microsoft.com/dynamics365/sales/copilot-overview -
13Microsoft 365 Copilot for Sales — OverviewM365 · Sales IntelligenceDocumentation for Microsoft 365 Copilot for Sales: capabilities in Outlook and Teams for email summaries, CRM-integrated meeting preparation, and suggested replies.
learn.microsoft.com/microsoft-sales-copilot/overview -
14Copilot in Dynamics 365 Field ServiceD365 Field Service · Mobile AIDocumentation covering Copilot capabilities in D365 Field Service, including mobile app AI guidance for field technicians and work-order summarisation.
learn.microsoft.com/dynamics365/field-service/copilot-in-field-service -
15Enable Copilot Capabilities in Finance and Operations AppsD365 Finance · Security PrerequisitesConfiguration guide including the Finance and Operations AI security role prerequisite for prebuilt Finance Copilot capabilities.
learn.microsoft.com/dynamics365/fin-ops-core/dev-itpro/copilot/enable-copilot -
16Agent Management in Dynamics 365 Supply Chain ManagementD365 SCM · Prebuilt Agent DiscoveryDocumentation for the Agent Management capability in D365 SCM — browse, preview, and evaluate the prebuilt AI agent catalog.
learn.microsoft.com/dynamics365/supply-chain/copilot/agent-management -
17Configure Hand-off to Omnichannel for Customer ServiceCopilot Studio · Contact CenterDocumentation for integrating Copilot Studio agents with Dynamics 365 Contact Center via Customer Engagement Hub, including the Escalation topic configuration and session context transfer.
learn.microsoft.com/microsoft-copilot-studio/configuration-hand-off-omnichannel -
18Solution Concepts in Power Platform ALMALM · SolutionsFoundational documentation for managed and unmanaged solutions in Power Platform: properties, differences, deployment behaviour, and ALM implications.
learn.microsoft.com/power-platform/alm/solution-concepts-alm -
19ALM Accelerator for Microsoft Power PlatformALM · Deployment PipelinesDocumentation and overview for the ALM Accelerator — Microsoft's recommended tooling for automated Power Platform solution lifecycle management through DEV → TEST → PROD.
learn.microsoft.com/power-platform/guidance/alm-accelerator/overview -
20Microsoft Purview for AI GovernanceGovernance · Compliance · AI AuditDocumentation for Microsoft Purview capabilities for AI — including AI Hub for resource inventory, sensitivity data access tracking, and audit log capabilities for AI agents.
learn.microsoft.com/purview/ai-microsoft-purview -
21Microsoft Responsible AI PrinciplesResponsible AI · EthicsMicrosoft's six Responsible AI principles — Fairness, Reliability & Safety, Privacy & Security, Inclusiveness, Transparency, and Accountability — and their architectural implementations.
microsoft.com/ai/responsible-ai -
22Power Platform Well-Architected FrameworkArchitecture · Design QualityMicrosoft's framework for designing high-quality Power Platform solutions: reliability, security, performance efficiency, operational excellence, and experience optimisation.
learn.microsoft.com/power-platform/well-architected/ -
23Power Platform Sensitivity Labels and Data Loss PreventionSecurity · Data ClassificationDocumentation for applying Microsoft Purview sensitivity labels to Power Platform and Dataverse data, and configuring data loss prevention policies.
learn.microsoft.com/power-platform/admin/wp-data-loss-prevention -
24Copilot Studio — Voice and TelephonyAgent Platform · VoiceDocumentation for building voice-enabled Copilot Studio agents and integrating with Dynamics 365 Contact Center telephony channels.
learn.microsoft.com/microsoft-copilot-studio/voice-overview -
25Generative Orchestration in Copilot StudioAgent Platform · OrchestrationDocumentation for generative AI orchestration in Copilot Studio — description-based topic routing, dynamic agent composition, and comparison with classic trigger-phrase orchestration.
learn.microsoft.com/microsoft-copilot-studio/advanced-generative-actions -
27Enterprise Framework for MCP and Agentic AI GovernanceChapter 6 Reference · MCP Governance · Architecture / Controls / Operating Model / Assurance / Australian AI AlignmentThe framework referenced in Chapter 6. Defines five pillars for governing Model Context Protocol and agentic AI adoption in enterprise contexts. Published independently at the URL below. GovernGlobal maps each pillar to its existing architecture decisions in Module 3 and the Chapter 6 applied analysis.
anir-a.github.io/Australia-AI-Guidance-Navigator/MCP-Agentic-AI-Guidance-Framework/ -
28Australia AI Navigator — 8 Principles, 6 Practices & Agentic AIChapter 7 Reference · Australian AI Governance · Three Governance Layers · Adoption LifecycleThe navigator referenced throughout Chapter 7. Aggregates and connects Australia's 8 AI Ethics Principles (DISR 2019), the AI6 Essential Practices (NAIC October 2025), and the May 2026 joint agentic AI advisory (ASD ACSC / CISA / NSA / CCCS / NCSC-NZ / NCSC-UK) into a single source-linked reference. Chapter 7 uses the Navigator's three-layer structure and its published agentic AI alignment table to audit GovernGlobal's existing architecture decisions.
anir-a.github.io/Australia-AI-Guidance-Navigator/ -
26Microsoft Cloud Adoption Framework — Responsible AIStrategy · Responsible AICAF guidance specific to Responsible AI adoption: assessment timing, governance integration, and the relationship between RAI principles and architecture decisions.
learn.microsoft.com/azure/cloud-adoption-framework/responsible-innovation/
§5 About This Publication
Publication Details
Plain language summary: This entire book is about Microsoft's products. Every feature, tool, and framework discussed belongs to Microsoft Corporation. We wrote a fictional story and teaching structure around those products to make them easier to understand. That story is ours. The products are Microsoft's.
Title: Building Intelligent Enterprises — The GovernGlobal Story: An Architect's Field Guide
Publisher: Govern Global Practice
Year: 2025
Version: 1.0
Format: Interactive HTML — single-file, no external runtime dependencies beyond Google Fonts CDN
Content scope: All technical product features, frameworks, and capabilities described are the intellectual property of Microsoft Corporation, referenced for educational commentary purposes only. Original narrative elements (GovernGlobal story, characters, teaching structure): CC BY 4.0.
Suggested citation: Govern Global Practice. (2025). Building Intelligent Enterprises — The GovernGlobal Story: An Architect's Field Guide. Govern Global. CC BY 4.0.
Scope of accuracy: Content reflects Microsoft product documentation available as of 2025. Microsoft products, features, and documentation URLs change over time. Verify all technical details against current official documentation at learn.microsoft.com before making architectural decisions.