Skip to content

Commit 21ccd0e

Browse files
authored
updates m6
1 parent fe26db5 commit 21ccd0e

9 files changed

Lines changed: 468 additions & 691 deletions
Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,5 @@
1-
Welcome to Module 6, which focuses on the design extensibility of AI solutions in enterprise environments. This module introduces solution architects to the foundational concepts, architectural patterns, and best practices for building scalable, secure, and customizable AI solutions using Microsoft platforms. Extensibility is a critical capability that enables organizations to tailor AI systems to their unique business processes, compliance requirements, and operational constraints.
1+
This module focuses on designing extensible AI solutions in enterprise environments. It introduces solution architects to the foundational concepts, architectural patterns, and best practices for building scalable, secure, and customizable AI solutions by using Microsoft platforms. Extensibility is a critical capability that enables organizations to tailor AI systems to their unique business processes, compliance requirements, and operational constraints.
22

3-
Throughout this module, you explore how to use custom models in Microsoft Foundry, design and operationalize agents within Microsoft 365 Copilot, and extend agent capabilities using Copilot Studioincluding advanced integration through the Model Context Protocol (MCP). The unit guide you through structured approaches for model and agent design, integration with enterprise systems, governance, lifecycle management, and professional visualizations that can be adapted for documentation and presentations.
3+
Throughout this module, you explore how to use custom models in Microsoft Foundry, design and operationalize agents within Microsoft 365 Copilot, and extend agent capabilities by using Copilot Studio, including advanced integration through the Model Context Protocol (MCP). The module guides you through structured approaches for model and agent design, integration with enterprise systems, governance, lifecycle management, and professional visualizations that can be adapted for documentation and presentations.
44

5-
By the end of this module, aren't equipped with expert-level guidance and practical frameworks to architect AI solutions that are not only robust and compliant, but also extensible to meet evolving business needs across diverse scenarios and platforms.
5+
By the end of this module, you are equipped with expert-level guidance and practical frameworks to architect AI solutions that are not only robust and compliant, but also extensible enough to meet evolving business needs across diverse scenarios and platforms.
Lines changed: 15 additions & 25 deletions
Original file line numberDiff line numberDiff line change
@@ -1,41 +1,31 @@
11
### Design extensibility of AI solutions — Summary and key takeaways
22

3-
Module 6 introduces solution architects to the principles and best practices for designing extensible AI solutions in enterprise environments, specifically leveraging Microsoft platforms. The module covers the use of custom models with Microsoft Foundry, agent design and operationalization in Microsoft 365 Copilot, extensibility strategies in Copilot Studio, and advanced integration using the Model Context Protocol (MCP). It emphasizes the importance of scalability, security, compliance, and adaptability in architecting AI systems that address unique organizational needs.
3+
This module introduces solution architects to the principles and best practices for designing extensible AI solutions in enterprise environments by using Microsoft platforms. The module covers the use of custom models with Microsoft Foundry, agent design and operationalization in Microsoft 365 Copilot, extensibility strategies in Copilot Studio, and advanced integration by using the Model Context Protocol (MCP). It emphasizes the importance of scalability, security, compliance, and adaptability in architecting AI systems that address unique organizational needs.
44

55
### Key takeaways
66

77
#### Custom models in Microsoft Foundry
88

9-
- Custom models are essential for scenarios requiring domain-specific reasoning, compliance, data sovereignty, unique workflows, and cost optimization.
10-
11-
- Foundry provides tools for data preparation, model training, evaluation, deployment, and governance, supporting full lifecycle management.
12-
13-
- Solution architects should follow a structured approach: define business objectives, assess data requirements, select the appropriate model path, integrate with enterprise systems, and validate results.
14-
15-
- Operationalizing custom models requires robust monitoring, governance, versioning, and deployment automation.
9+
- Custom models are essential for scenarios requiring domain-specific reasoning, compliance, data sovereignty, unique workflows, and cost optimization.
10+
- Foundry provides tools for data preparation, model training, evaluation, deployment, and governance, supporting full lifecycle management.
11+
- Solution architects should follow a structured approach: define business objectives, assess data requirements, select the appropriate model path, integrate with enterprise systems, and validate results.
12+
- Operationalizing custom models requires robust monitoring, governance, versioning, and deployment automation.
1613

1714
#### Designing agents in Microsoft 365 Copilot
1815

19-
- Copilot agents are modular, instruction-driven components that automate tasks, retrieve information, and collaborate within Microsoft 365 apps.
20-
21-
- Effective agent design centers on clear intent, strict guardrails, scoped permissions, and alignment with business goals and data boundaries.
22-
23-
- Collaborative agents can support sequential, parallel, and orchestrated workflows, improving cross-app productivity and user experience.
24-
25-
- Lifecycle management includes monitoring agent quality, updating instructions, enforcing access control, and versioning.
16+
- Copilot agents are modular, instruction-driven components that automate tasks, retrieve information, and collaborate within Microsoft 365 apps.
17+
- Effective agent design centers on clear intent, strict guardrails, scoped permissions, and alignment with business goals and data boundaries.
18+
- Collaborative agents can support sequential, parallel, and orchestrated workflows, improving cross-app productivity and user experience.
19+
- Lifecycle management includes monitoring agent quality, updating instructions, enforcing access control, and versioning.
2620

2721
#### Agent extensibility in Copilot Studio
2822

29-
- Extensibility is implemented at four layers: instruction-level, skills/capabilities, integration, and pro-code customization via Visual Studio Code.
30-
31-
- Modular and reusable agent components enable faster updates, better compliance, and long-term maintainability.
32-
33-
- Multi-agent collaboration and domain-context patterns allow agents to specialize and adapt to different business environments.
23+
- Extensibility is implemented at four layers: instruction-level, skills/capabilities, integration, and pro-code customization through Visual Studio Code.
24+
- Modular and reusable agent components enable faster updates, better compliance, and long-term maintainability.
25+
- Multi-agent collaboration and domain-context patterns allow agents to specialize and adapt to different business environments.
3426

3527
#### Model Context Protocol (MCP) in Copilot Studio
3628

37-
- MCP provides a standardized contract for agents to retrieve and interpret structured business context, ensuring consistent reasoning and compliance.
38-
39-
- MCP is particularly valuable for Dynamics 365 Finance & Operations scenarios, enabling agents to access business entities, workflows, and domain models.
40-
41-
- MCP-enabled agents improve accuracy, reduce incorrect information, enhance auditability, and
29+
- MCP provides a standardized contract for agents to retrieve and interpret structured business context, ensuring consistent reasoning and compliance.
30+
- MCP is particularly valuable for Dynamics 365 Finance & Operations scenarios, enabling agents to access business entities, workflows, and domain models.
31+
- MCP-enabled agents improve accuracy, reduce incorrect information, enhance auditability, and support policy-aligned actions across enterprise workflows.

learn-pr/wwl/design-extensibility-ai-solutions/includes/2-design-ai-solutions-custom-models-microsoft-foundry.md

Lines changed: 74 additions & 61 deletions
Original file line numberDiff line numberDiff line change
@@ -17,124 +17,137 @@ Solution architects determine when custom AI models are needed by evaluating bus
1717

1818
### Appropriate scenarios
1919

20-
**Domain-specific language and reasoning**<br>Industries such as legal, healthcare, engineering, finance, and manufacturing require AI models that understand specialized terminology and follow domain-specific logic.
20+
#### Domain-specific language and reasoning
2121

22-
**High-impact decision processes**<br>Custom models are used when accuracy directly affects compliance, financial outcomes, or operational safety.
22+
Industries such as legal, healthcare, engineering, finance, and manufacturing require AI models that understand specialized terminology and follow domain-specific logic.
2323

24-
**Data sovereignty and governance mandates**<br>Custom models enable organizations to determine exactly how data is processed, stored, evaluated, and monitored.
24+
#### High-impact decision processes
2525

26-
**Unique workflows or personalization requirements**<br>Pre-built copilots may not support custom interaction patterns, long-running processes, or proprietary toolchains.
26+
Custom models are used when accuracy directly affects compliance, financial outcomes, or operational safety.
2727

28-
**Cost optimization for high-volume inference**<br>Small, specialized custom models can provide performance and cost advantages over large foundation models.
28+
#### Data sovereignty and governance mandates
2929

30-
## Understanding architecture foundations in Microsoft Foundry
30+
Custom models enable organizations to determine exactly how data is processed, stored, evaluated, and monitored.
3131

32-
Microsoft Foundry provides an end-to-end platform for custom model development, including tools for data preparation, training, evaluation, deployment, observability, and governance.
32+
#### Unique workflows or personalization requirements
3333

34-
### Key architectural elements
34+
Pre-built copilots may not support custom interaction patterns, long-running processes, or proprietary toolchains.
3535

36-
**Model Catalog**<br>Offers base models that can be fine-tuned or enhanced using enterprise data and specialized tasks.
36+
#### Cost optimization for high-volume inference
3737

38-
**Training and Fine-tuning Pipelines**<br>Help orchestrate data ingestion, labeling, evaluation, and iterative improvements at scale.
38+
Small, specialized custom models can provide performance and cost advantages over large foundation models.
3939

40-
**Agent and Tooling Integration**<br>Custom models can be embedded into Foundry agents and orchestrations to support multi-step reasoning and automated workflows.
40+
## Understanding architecture foundations in Microsoft Foundry
4141

42-
**Responsible AI Controls**<br>Includes content filtering, safety evaluation, transparency artifacts, policy enforcement, and auditability.
42+
Microsoft Foundry provides an end-to-end platform for custom model development, including tools for data preparation, training, evaluation, deployment, observability, and governance.
4343

44-
**Deployment Topologies**
44+
### Key architectural elements
4545

46-
Hosted secure environments
46+
#### Model catalog
4747

48-
Private networking deployments
48+
Offers base models that can be fine-tuned or enhanced using enterprise data and specialized tasks.
4949

50-
Integration with Azure Kubernetes Service and Foundry runtime environments
50+
#### Training and fine-tuning pipelines
5151

52-
## Designing AI solutions with custom models
52+
Help orchestrate data ingestion, labeling, evaluation, and iterative improvements at scale.
5353

54-
Solution architects should follow a structured, repeatable design approach to ensure models align with business objectives.
54+
#### Agent and tooling integration
5555

56-
### Step 1 Define the business objectives
56+
Custom models can be embedded into Foundry agents and orchestrations to support multi-step reasoning and automated workflows.
5757

58-
Identify measurable outcomes (accuracy goals, time-saved targets, cost-efficiency goals).
58+
#### Responsible AI controls
5959

60-
Map objectives to use cases where custom models outperform standard copilots.
60+
Includes content filtering, safety evaluation, transparency artifacts, policy enforcement, and auditability.
6161

62-
### Step 2 Assess data requirements
62+
#### Deployment topologies
6363

64-
Evaluate available proprietary datasets.
64+
- Hosted secure environments.
65+
- Private networking deployments.
66+
- Integration with Azure Kubernetes Service and Foundry runtime environments.
6567

66-
Identify gaps in labeling, quality, diversity, or structure.
68+
## Designing AI solutions with custom models
6769

68-
Ensure governance policies allow data to be used in model training.
70+
Solution architects should follow a structured, repeatable design approach to ensure models align with business objectives.
6971

70-
### Step 3 Select the custom model path
72+
### Step 1. Define the business objectives
7173

72-
#### Typical options include
74+
- Identify measurable outcomes, such as accuracy goals, time-saved targets, and cost-efficiency goals.
75+
- Map objectives to use cases where custom models outperform standard copilots.
7376

74-
**Fine-tuning foundation models**<br>Adjust behavior using domain datasets without full retraining.
77+
### Step 2. Assess data requirements
7578

76-
**Training domain-built small models**<br>Useful for lightweight tasks requiring speed and edge compatibility.
79+
- Evaluate available proprietary datasets.
80+
- Identify gaps in labeling, quality, diversity, or structure.
81+
- Ensure governance policies allow data to be used in model training.
7782

78-
**Hybrid architectures**<br>Combining custom models with prebuilt copilots for augmented reasoning.
83+
### Step 3. Select the custom model path
7984

80-
### Step 4 Integration with enterprise systems
85+
Typical options include:
8186

82-
#### Custom models should integrate with
87+
#### Fine-tuning foundation models
8388

84-
Dynamics 365 applications
89+
Adjust behavior using domain datasets without full retraining.
8590

86-
Azure Functions and Logic Apps
91+
#### Training domain-built small models
8792

88-
Foundry agent workflows
93+
Useful for lightweight tasks requiring speed and edge compatibility.
8994

90-
Azure AI Search and data stores
95+
#### Hybrid architectures
9196

92-
Business process automation pipelines
97+
Combine custom models with prebuilt copilots for augmented reasoning.
9398

94-
### Step 5 Validation and evaluation
99+
### Step 4. Integrate with enterprise systems
95100

96-
#### Establish a rigorous testing plan
101+
Custom models should integrate with:
97102

98-
Scenario-based evaluations
103+
- Dynamics 365 applications.
104+
- Azure Functions and Logic Apps.
105+
- Foundry agent workflows.
106+
- Azure AI Search and data stores.
107+
- Business process automation pipelines.
99108

100-
Safety and bias analysis
109+
### Step 5. Validate and evaluate
101110

102-
Stress, latency, and scaling tests
111+
Establish a rigorous testing plan that includes:
103112

104-
ROI measurement and business validation
113+
- Scenario-based evaluations.
114+
- Safety and bias analysis.
115+
- Stress, latency, and scaling tests.
116+
- ROI measurement and business validation.
105117

106118
## Operationalizing custom models in Foundry
107119

108-
Modern AI systems require robust operational frameworks, especially with custom AI models. Foundry has tools to help support these custom AI models for long term feasibility.
120+
Modern AI systems require robust operational frameworks, especially for custom AI models. Foundry has tools to support these models for long-term feasibility.
109121

110122
### Key operational components
111123

112-
**Model Monitoring and Observability**<br>Track drift, performance degradation, user friction areas, latency, and unexpected model outputs.
124+
#### Model monitoring and observability
113125

114-
**Governance and Compliance Controls**<br>Ensure every deployment meets enterprise privacy, security, and regulatory requirements.
126+
Track drift, performance degradation, user friction areas, latency, and unexpected model outputs.
115127

116-
**Versioning and Lifecycle Management**<br>Maintain clear model version trails, update pipelines, and rollback strategies.
128+
#### Governance and compliance controls
117129

118-
**Deployment Automation (MLOps/GenAIOps)**<br>Automate validations, approval workflows, and environment-specific deployments.
119-
120-
### Custom model decision matrix
130+
Ensure every deployment meets enterprise privacy, security, and regulatory requirements.
121131

122-
Decision Factor | Standard Copilot | Custom Model (Foundry)
132+
#### Versioning and lifecycle management
123133

124-
-----------------------------------------------------------------------
134+
Maintain clear model version trails, update pipelines, and rollback strategies.
125135

126-
Domain specificity needed | Low | High
136+
#### Deployment automation (MLOps/GenAIOps)
127137

128-
Compliance restrictions | Moderate | High
138+
Automate validations, approval workflows, and environment-specific deployments.
129139

130-
Performance requirements | Medium | High
131-
132-
Data confidentiality | Medium | Full control
133-
134-
Workflow complexity | Low/Medium | High
140+
### Custom model decision matrix
135141

136-
Inference cost optimization | Moderate | High (small language models)
142+
| Decision factor | Standard Copilot | Custom model (Foundry) |
143+
| --- | --- | --- |
144+
| Domain specificity needed | Low | High |
145+
| Compliance restrictions | Moderate | High |
146+
| Performance requirements | Medium | High |
147+
| Data confidentiality | Medium | Full control |
148+
| Workflow complexity | Low/Medium | High |
149+
| Inference cost optimization | Moderate | High (small language models) |
137150

138151
## References
139152

140-
[https://learn.microsoft.com/en-us/training/modules/choose-ai-agent-development-path/](/training/modules/choose-ai-agent-development-path/)
153+
[https://learn.microsoft.com/en-us/training/modules/choose-ai-agent-development-path/](/training/modules/choose-ai-agent-development-path/)

0 commit comments

Comments
 (0)