Updated files to ensure GitHub Copilot SDK is fully spelled out

Author: ChrisHowd

learn-pr/wwl-azure/develop-ai-enabled-apps-using-github-copilot-sdk/includes/10-summary.md

@@ -4,7 +4,7 @@ You examined real-world scenarios where AI agents provide business value, from e
 
 The main takeaway from this module is that the GitHub Copilot SDK handles the complex infrastructure of agent orchestration—session management, tool calling, context tracking, and model communication—so you can focus on defining the tools and business logic that make your agent useful.
 
-You can apply this knowledge to build AI agents for your own applications. Start by identifying a workflow in your organization that involves multiple steps, data lookups, and decision making. Define the tools the agent would need, write a focused system prompt, and use the Copilot SDK to bring the agent to life.
+You can apply this knowledge to build AI agents for your own applications. Start by identifying a workflow in your organization that involves multiple steps, data lookups, and decision making. Define the tools the agent would need, write a focused system prompt, and use the GitHub Copilot SDK to bring the agent to life.
 
 ## Learn more
 

learn-pr/wwl-azure/develop-ai-enabled-apps-using-github-copilot-sdk/includes/2-what-ai-agent.md

@@ -49,3 +49,7 @@ The following table compares the capabilities of chatbots, automation scripts, a
 | **Error handling** | Falls back to default | Stops or retries | Reasons about alternatives |
 
 AI agents combine the language understanding of chatbots with the action-oriented power of automation scripts, amplified by AI's ability to reason and adapt.
+
+## Summary
+
+AI agents are autonomous AI entities that can reason, plan, and take actions to achieve complex goals. They differ from chatbots in their ability to handle multi-step tasks, use tools, and maintain context. AI agents are ideal for scenarios that require integration across systems, decision-making, and iterative execution. Frameworks like ReAct and RAG enable these capabilities by combining reasoning with tool use and retrieval of external information. When designed with appropriate guardrails, AI agents can deliver significant business value while operating safely and effectively.

learn-pr/wwl-azure/develop-ai-enabled-apps-using-github-copilot-sdk/includes/3-what-github-copilot-sdk.md

@@ -4,7 +4,7 @@ The GitHub Copilot SDK is a multi-platform toolkit (currently in Technical Previ
 
 Building a full-featured AI agent from the ground up is complex. You need to handle conversation state management across turns, decide when to call which external API, ensure the AI's responses stay within boundaries, manage multiple AI models for different tasks, and implement safety measures. Building agentic workflows from scratch means you've essentially built a mini platform before you even get to your business logic.
 
-The Copilot SDK removes that complexity by providing a prebuilt, production-tested agent engine. The SDK handles authentication, model management, chat sessions, and streaming. You focus on what gets built on top of those building blocks—your domain-specific tools and business logic.
+The GitHub Copilot SDK removes that complexity by providing a prebuilt, production-tested agent engine. The SDK handles authentication, model management, chat sessions, and streaming. You focus on what gets built on top of those building blocks—your domain-specific tools and business logic.
 
 ## Architecture overview
 
@@ -49,7 +49,7 @@ The SDK isn't tied to one AI model. It supports multiple AI models and allows dy
 
 ### Real-time streaming
 
-The SDK supports streaming responses, meaning as the AI generates output, you can stream it to your app. For example, you can stream tokens to show a typing indicator or partial answer in a chat UI. This makes the experience more interactive and responsive.
+The SDK supports streaming responses, meaning as the AI generates output, you can stream it to your app. For example, you can stream tokens to show a typing indicator or partial answer in a chat UI. This behavior makes the experience more interactive and responsive.
 
 ### Authentication and security
 
@@ -135,3 +135,7 @@ To use the GitHub Copilot SDK in a .NET application, your environment needs:
 - A GitHub account with an active Copilot subscription (or your own API keys for BYOK).
 - The `GitHub.Copilot.SDK` NuGet package.
 - The `Microsoft.Extensions.AI` NuGet package (for defining tools using `AIFunctionFactory`).
+
+## Summary
+
+The GitHub Copilot SDK provides a powerful, production-ready platform for building AI agents in your applications. By abstracting away the complexities of agent orchestration, tool integration, and context management, the SDK lets you focus on defining your agent's capabilities and business logic. With support for multiple languages, real-time streaming, and flexible authentication options, the GitHub Copilot SDK is a versatile choice for adding AI agent functionality to a wide range of applications.

learn-pr/wwl-azure/develop-ai-enabled-apps-using-github-copilot-sdk/includes/4-examine-ai-agent-use-cases.md

@@ -1,16 +1,18 @@
-Now that you understand what AI agents are and what the Copilot SDK offers, it's time to explore how AI agents apply in real business contexts. This unit examines five scenarios where AI agents go beyond simple question-and-answer interactions to deliver measurable business value. Each scenario describes the agent's role, how it works, and why it matters. Pay particular attention to the e-commerce scenario, which closely mirrors the exercise later in this module.
+Now that you understand what AI agents are and what the GitHub Copilot SDK offers, it's time to explore how AI agents are used in real business contexts. This unit examines five scenarios where AI agents go beyond simple question-and-answer interactions to deliver measurable business value. Each scenario describes the agent's role, how it works, and why it matters.
 
 ## E-commerce customer service agent
 
 An online retail company deploys an AI agent to handle customer support and order operations. This agent is integrated into the company's web portal and assists customers with tasks like checking order status, initiating returns, processing refunds, and answering product questions. Rather than just answering questions, the agent takes actions in the order system on the customer's behalf.
 
-### How it works
+### How agents work in a customer service scenario
+
+When a customer says, "I received the wrong item, order 12345. I want to return it," the agent identifies the order number and issue. It calls a tool to retrieve order details from the backend system, verifies that the item was indeed incorrect, and then initiates a return request through another tool. The agent can also proactively offer a refund or replacement based on company policy.
 
 The agent connects to the company's backend APIs through registered tools. It has tools for looking up orders, creating return requests, issuing refunds, and sending customer communications. When a customer says, "My order arrived damaged, what can I do?", the agent verifies the order details through an API call, then responds with both empathy and action: "I've initiated a return for you and scheduled a courier pickup for tomorrow. You'll receive a refund that's applied to your original payment method."
 
 If the agent encounters a request outside its capability (like a complex policy dispute), it escalates to a human support representative and provides the context it gathered during the conversation.
 
-### Why it matters
+### Why agents matter in a customer service scenario
 
 This type of agent provides instant, 24/7 support that resolves issues rather than just providing information. The support team can focus on complex cases that require human judgment, while the agent handles routine inquiries autonomously. Guardrails ensure the agent operates within boundaries—for example, it won't process a refund above a certain amount without human approval, and it logs all actions for audit purposes.
 
@@ -19,34 +21,60 @@ This type of agent provides instant, 24/7 support that resolves issues rather th
 
 ## Sales CRM lead management agent
 
-A software company integrates an AI agent with their Customer Relationship Management (CRM) system to qualify leads, enrich contact records, and handle initial customer outreach. When a new lead arrives, the agent gathers information about the prospective customer, scores the lead based on predefined criteria, and updates the CRM record accordingly.
+A software company integrates an AI agent with their Customer Relationship Management (CRM) system to qualify leads, enrich contact records, and handle initial customer outreach.
+
+### How agents work in a sales CRM scenario
+
+When a new lead arrives, the agent gathers information about the prospective customer, scores the lead based on predefined criteria, and updates the CRM record accordingly.
 
 For high-scoring leads, the agent can assign the lead to a sales representative and draft a personalized introduction email. It can also answer basic product questions from prospects via email, acting as an automated sales development representative. The agent always involves a human salesperson when conversations move beyond the basics.
 
+### Why agents matter in a sales CRM scenario
+
 This approach automates the time-consuming parts of sales—research, data entry, and initial outreach—so that sales representatives can focus on qualified prospects and closing deals. Every inquiry receives a quick, informed follow-up, and lead scoring is applied consistently across all prospects.
 
 ## Finance and accounting automation agent
 
-An enterprise finance department uses an AI agent to handle routine financial operations: invoice processing, expense reconciliation, and transaction matching. Each day, the agent processes incoming invoices by extracting relevant data (vendor name, amounts, due dates), then cross-references them against purchase orders in the enterprise resource planning (ERP) system.
+An enterprise finance department uses an AI agent to handle routine financial operations: invoice processing, expense reconciliation, and transaction matching.
+
+### How agents work in a finance automation scenario
+
+Each day, the agent processes incoming invoices by extracting relevant data (vendor name, amounts, due dates), then cross-references them against purchase orders in the enterprise resource planning (ERP) system.
 
 If the invoice matches the purchase order within acceptable variance thresholds, the agent approves it for payment. When the agent detects discrepancies—like an invoice amount that exceeds the purchase order by more than the allowed tolerance—it flags the issue and routes it to a human accountant with a detailed explanation.
 
-At month-end, the agent reconciles bank transactions against the company's ledger, identifying unmatched entries and creating draft journal entries for review. This agent follows its rules precisely—it never approves an invoice that exceeds policy thresholds—which improves both speed and compliance. Accounting staff shift from data entry to exception handling and analysis.
+At month-end, the agent reconciles bank transactions against the company's ledger, identifying unmatched entries and creating draft journal entries for review.
+
+### Why agents matter in a finance automation scenario
+
+This agent follows its rules precisely—it never approves an invoice that exceeds policy thresholds—which improves both speed and compliance. Accounting staff shift from data entry to exception handling and analysis.
 
 ## Supply chain and inventory management agent
 
-A retail business uses an AI agent to monitor inventory levels across warehouses, track supply shipments, and respond to real-time changes in demand or supply. The agent continuously checks stock levels, incoming shipment ETAs, and current sales velocity.
+A retail business uses an AI agent to monitor inventory levels across warehouses, track supply shipments, and respond to real-time changes in demand or supply.
+
+### How agents work in a supply chain scenario
+
+The agent continuously checks stock levels, incoming shipment ETAs, and current sales velocity.
 
 When the agent detects that a product is selling faster than forecasted in one region while another region has surplus stock, it can create a transfer request to rebalance inventory. If a supplier shipment is delayed, the agent updates inventory availability forecasts and alerts supply chain managers with recommendations. It can also identify slow-moving products and suggest redistribution or order adjustments.
 
-This type of agent helps reduce both stockouts (lost sales) and excess inventory (wasted capital). It makes the supply chain more responsive by detecting and addressing problems faster than periodic human reviews allow.
+### Why agents matter in a supply chain scenario
+
+This type of agent helps reduce both stockouts (lost sales) and excess inventory (wasted expenditures). It makes the supply chain more responsive by detecting and addressing problems faster than periodic human reviews allow.
 
 ## IT operations and incident response agent
 
-A technology company uses an AI agent as a first responder to system alerts and incidents. When a monitoring alert fires (such as high CPU usage on a database server), the agent investigates by running diagnostic scripts, analyzing logs, and attempting known remediation steps.
+A technology company uses an AI agent as a first responder to system alerts and incidents.
+
+### How agents work in an IT operations scenario
+
+When a monitoring alert fires (such as high CPU usage on a database server), the agent investigates by running diagnostic scripts, analyzing logs, and attempting known remediation steps.
 
 For example, if the agent detects a long-running query causing high CPU, it can terminate the query and verify that performance returns to normal. If it resolves the issue, it logs the actions taken and closes the incident. If the issue persists after exhausting its troubleshooting steps, the agent escalates to a human engineer with the diagnostic context it gathered.
 
+### Why agents matter in an IT operations scenario
+
 This agent is particularly valuable for its speed—it can begin investigating within seconds of an alert, rather than the minutes it takes for a human to notice and respond. Initial deployments typically restrict the agent to safe, reversible actions (like restarting services or clearing temp files) and require human approval for riskier operations.
 
 ## Comparing scenarios
@@ -62,3 +90,7 @@ The following table summarizes the key characteristics of each scenario:
 | IT operations | DevOps | Investigates and remediates system alerts | Faster incident response with lower downtime |
 
 A pattern emerges across all five scenarios: AI agents handle complex, multi-step tasks that previously required a human's constant attention. They serve as force multipliers for teams by taking on routine work and letting humans focus on exceptions and strategy.
+
+## Summary
+
+AI agents are transforming how businesses operate across domains. From customer service to finance to IT operations, agents are taking on tasks that require reasoning, tool use, and context management. By automating multi-step workflows and integrating with real systems, AI agents deliver faster, more consistent outcomes while freeing human workers to focus on higher-value activities. The GitHub Copilot SDK provides a powerful platform for building these agents, enabling you to bring the benefits of AI-driven automation to your applications.

learn-pr/wwl-azure/develop-ai-enabled-apps-using-github-copilot-sdk/includes/5-design-ai-agents.md

@@ -26,7 +26,7 @@ The GitHub Copilot SDK provides this planner as a built-in feature. The SDK's ag
 
 Unlike a stateless API call, agents maintain contextual memory throughout a session. The agent's *awareness* includes conversation history, tool outputs, and any data retrieved during previous steps. Memory is what enables coherence: when a user says "actually, it was the wrong color," the agent knows that "it" refers to the item discussed earlier.
 
-The Copilot SDK manages short-term memory automatically by tracking conversation history within a session. For sessions that might exceed the model's context window, the SDK's infinite sessions feature compacts older context to prevent token overflow while preserving essential information.
+The GitHub Copilot SDK manages short-term memory automatically by tracking conversation history within a session. For sessions that might exceed the model's context window, the SDK's infinite sessions feature compacts older context to prevent token overflow while preserving essential information.
 
 ### Policies and guardrails
 
@@ -37,7 +37,7 @@ Because AI agents take autonomous actions, you need constraints to ensure they o
 - **Safety filters**: Instruct the agent (through the system prompt) to stay within its domain and avoid revealing internal information.
 - **Fallback and escalation**: Design what happens when the agent can't resolve a request. This guardrail typically means handing off to a human with the context the agent gathered.
 
-In the Copilot SDK, guardrails come from three sources: the tools you expose (which inherently limit what the agent can do), the system prompt (which guides behavior), and code-level controls in your tool handlers and session hooks.
+In the GitHub Copilot SDK, guardrails come from three sources: the tools you expose (which inherently limit what the agent can do), the system prompt (which guides behavior), and code-level controls in your tool handlers and session hooks.
 
 ## Agent workflow in practice
 
@@ -65,12 +65,16 @@ Consider how an e-commerce return agent handles a request:
 
 The agent used two tools and reasoned through multiple steps, but from the user's perspective, it was a single smooth interaction.
 
-## Design decisions for the Copilot SDK
+## Design decisions for the GitHub Copilot SDK
 
-When designing an agent to build with the Copilot SDK, focus on three areas:
+When designing an agent to build with the GitHub Copilot SDK, focus on three areas:
 
 - **Context**: What information does the agent need at the start of each session? The context typically includes a system prompt that defines the agent's role and behavior guidelines, plus any user-specific data that enables personalized responses.
 - **Tools**: What actions should the agent be able to take? Define each tool with a clear name, description, and parameter schema. Implement the business logic in the tool handler.
 - **Policies**: What rules must the agent follow? Encode policies as system prompt instructions, tool handler validations, or session hook logic.
 
 You also need to plan for failure modes. If a tool call fails, should the agent retry, try an alternative approach, or escalate? These decisions can be encoded in the system prompt ("if a tool returns an error, inform the user and offer alternatives") or handled programmatically in error-handling hooks.
+
+## Summary
+
+Designing an AI agent involves defining its reasoning capabilities, the tools it can use, how it maintains context, and the guardrails that ensure safe operation. The GitHub Copilot SDK provides a powerful framework for building agents with these components. By carefully designing the system prompt, selecting appropriate tools, and implementing policies, you can create agents that deliver real business value while operating within defined boundaries. In the next unit, you'll see how to apply these design principles in practice by building a sample agent with the GitHub Copilot SDK.