Implementing Tool Usage in Copilot Studio Topics

AB-620 By islever Editorial Last updated

Add tools to agents Configure topics

Short answer

1. Let the agent decide when to run a tool based on user input: Enable generative orchestration. 2. Run a specific agent flow at a defined step in a topic: Add a tool node. 3. Use a connector action to retrieve data during a conversation: Add a tool node.

Question

DRAG DROP
Case Study
This is a case study. Case studies are not timed separately from other exam sections. You can use as much exam time as you would like to complete each case study. However, there might be additional case studies or other exam sections. Manage your time to ensure that you can complete all the exam sections in the time provided. Pay attention to the Exam Progress at the top of the screen so you have sufficient time to complete any exam sections that follow this case study.
To answer the case study questions, you will need to reference information that is provided in the case. Case studies and associated questions might contain exhibits or other resources that provide more information about the scenario described in the case. Information provided in an individual question does not apply to the other questions in the case study.
A Review Screen will appear at the end of this case study. From the Review Screen, you can review and change your answers before you move to the next exam section. After you leave this case study, you will NOT be able to return to it.
To start the case study
To display the first question in this case study, select the "Next" button. To the left of the question, a menu provides links to information such as business requirements, the existing environment, and problem statements. Please read through all this information before answering any questions. When you are ready to answer a question, select the "Question" button to return to the question.
Background
Blue Yonder Airlines is a global carrier headquartered in Los Angeles, California, operating domestic and international flights. The company serves millions of passengers annually through its website, mobile app, and call centers. To improve customer service efficiency and reduce call center volume, Blue Yonder is deploying an AI agent in Microsoft Copilot Studio.
The agent will handle customer inquiries across multiple channels – web chat, mobile app, and Microsoft Teams (for internal support staff). It will answer questions, retrieve data from enterprise systems, and escalate to human agents when needed.
The project is led by a cross-function team:
Product manager: Defines requirements and success metrics.
Lead agent author: Designs topics, intents, and generative behavior.
Flow designers: Build agent flows and integrations.
IT/security and compliance: Oversees identity, data protection, and Responsible AI (RAI) compliance.
Current environment
Channels
Public website: Embedded web chat
Mobile app: In-app chatbot
Microsoft Teams: Internal support agent access
Identity and access
Customers: Anonymous access for general inquiries (e.g., flight status, baggage policy).
Authentication is required for personal data access (e.g., bookings, loyalty points).
Internal staff: Authenticate via Microsoft Entra ID.
Data sources
Reservation and Ticketing System (internal): REST API, no prebuilt connector with custom enterprise database.
Flight Status and Weather APIs (external): REST APIs with API keys.
Customer Support Knowledge Base: SharePoint library with PDFs and policy documents.
Loyalty Program Data: Stored in Dynamics 365 and Dataverse.
Travel Advisory Content: Uses REST API with partner services.
Integration mechanisms
Custom connectors must be used for internal APIs that lack prebuilt connectors.
HTTP request nodes may be used for lightweight external APIs.
Knowledge sources must be used for unstructured content.
Agent flows must be used to encapsulate reusable logic (e.g., rebooking).
Business requirements
Omnichannel support
Deploy the agent across web, mobile, and Teams with a consistent user experience. The Teams deployment must also support internal staff.
Self-service capabilities
The agent must handle common inquiries such as:
Flight status
Booking and rebooking
Loyalty program questions
Travel policies and baggage rules
Human escalation
If the agent cannot resolve an issue or the user requests help, it must:
Escalate to a human agent.
Transfer the conversation transcript and relevant context.
Redact any sensitive personal data before escalation.
Knowledge integration
The agent must use scalable methods for knowledge integration and must not rely on manually authored Q&A topics for each document.
Performance metrics
First-contact resolution: +25%
Tier-1 call deflection: ≥20%
Response time: 90% of queries answered within 30 seconds
Accuracy: ≥95% for known FAQs
CSAT: ≥85% for AI-handled interactions
Technical requirements
Platform constraints
No custom code is permitted; only Copilot Studio's built-in tools may be used.
All backend logic must be implemented using agent flows.
Markdown must be used for formatting (e.g., bold, bullet points); HTML is not supported.
Authentication
Sign-in is required for personal data access.
Anonymous access is allowed for general inquiries.
User identity must be used for data access; shared or builder credentials must not be used.
Compliance and security
Power Platform DLP policies must be enforced to block unauthorized data flows.
Responsible AI content moderation filters must be enabled.
Prompt modifications must be added to enforce tone, disclaimers, and refusal behavior.
Disclaimers must be applied consistently across all generative responses. Manual edits to individual topics must be avoided.
Monitoring and maintenance
All conversations and actions must be logged for auditing.
Weekly reviews of transcripts and metrics must be conducted.
Issues and constraints
API rate limits: External APIs (e.g., flight status) have usage limits. Agent flows must handle retries and caching to avoid exceeding quotas.
Knowledge base limits: Copilot Studio has limits on the number and size of indexed documents. Large files must be split or summarized.
Generative answer risks: Generative responses must be constrained to avoid policy violations. Prompt modifications and filters must be used to enforce tone, safety, and compliance.
User input variability: Users phrase questions in diverse ways. Topics must include varied trigger phrases and fallback handling.
Authentication UX: The agent must clearly explain when sign-in is required and handle transitions smoothly across channels.
Problem statement
Blue Yonder Airlines must deploy a secure, scalable, and policy-compliant AI agent using Microsoft Copilot Studio. The agent must deliver accurate, helpful, and safe responses across multiple channels, integrate with enterprise systems, and support both anonymous and authenticated users. It must adhere to strict data protection and Responsible AI standards while improving customer service efficiency and satisfaction.
You need to implement tool usage in topics that meet the Blue Yonder design and governance requirements.
Which implementation method should you use for each requirement? To answer, move the appropriate implementation methods to the correct requirements. You may use each implementation method once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
Exhibit: Implementing Tool Usage in Copilot Studio Topics

Key Takeaways

The main trap is confusing generative orchestration with explicit tool nodes; use generative orchestration for dynamic, intent-based tool selection and tool nodes for fixed, procedural steps in a topic flow.

Learn how to implement tool usage in Microsoft Copilot Studio topics using generative orchestration and tool nodes to meet enterprise integration requirements.

Common mistake: Candidates often select 'Add a tool node' for all requirements because they see tools being used. However, this fails for the first requirement because generative orchestration is specifically designed for dynamic decision-making, whereas tool nodes enforce a static workflow path.

Expert Analysis

To meet Blue Yonder Airlines' requirements, you must select the appropriate implementation method for each specific scenario based on how Copilot Studio handles tool invocation. The core distinction lies between letting the AI decide dynamically versus enforcing a specific workflow step.

For the requirement to "Let the agent decide when to run a tool based on user input," the correct implementation is Enable generative orchestration. This feature allows the large language model to analyze the user's natural language query and automatically determine which available tools are relevant and when to invoke them. It is ideal for scenarios where the path to resolution varies significantly based on user intent, such as general inquiries about flight status or baggage policies where the specific API call depends entirely on what the user asks.

For the requirement to "Run a specific agent flow at a defined step in a topic," the correct implementation is Add a tool node. Tool nodes are used within explicit topic flows to execute a specific action, such as calling an agent flow for rebooking or retrieving loyalty data, at a predetermined point in the conversation. This ensures deterministic behavior where the flow logic controls the sequence of operations, rather than leaving it to the LLM's discretion.

For the requirement to "Use a connector action to retrieve data during a conversation," the correct implementation is also Add a tool node. While connectors provide the interface to external systems (like the Reservation System or Flight Status APIs), invoking that connector's action within a topic requires adding a tool node. This explicitly triggers the connector action at the desired point in the topic flow to fetch or update data, ensuring the interaction follows the designed process rather than relying on generative inference.

Exam Strategy

When faced with drag-and-drop questions involving Copilot Studio features, carefully distinguish between 'dynamic/intelligent' behaviors and 'explicit/procedural' actions. Look for keywords like 'decide,' 'based on user input,' or 'intelligent' which point to Generative Orchestration. Conversely, look for keywords like 'defined step,' 'specific flow,' or 'explicitly trigger' which indicate the use of Tool Nodes or explicit topic actions. Always map the requirement's control level to the feature's capability.

Frequently Asked Questions

What is the difference between generative orchestration and a tool node?

Generative orchestration allows the AI to dynamically choose which tool to use based on the user's query. A tool node is a static component added to a topic that explicitly executes a specific tool or action at a set point in the conversation flow.

Can I use a tool node to let the AI decide which tool to use?

No. If you add a tool node, you are forcing the topic to execute that specific tool at that specific time. To allow the AI to decide, you must enable generative orchestration instead.

How do I integrate a custom connector into a topic?

You must first create the custom connector in Power Platform. Then, in Copilot Studio, add a tool node to your topic and select the connector action as the tool to be invoked at that step.

More AB-620 FAQ →

Discussion 3 contributions

Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.

From public community threads 3

  1. faisalronnie 👍 10
    Let the agent decide when to run a tool based on user input. → Enable generative orchestration Run a specific agent flow at a defined step in a topic. → Add a tool node Use a connector action to retrieve data during a conversation. → Add a tool node
  2. Joselito79 👍 3
    ✅ Enable generative orchestration Why? Generative orchestration allows Copilot Studio to determine which tool to use and when, based on what the user asks. ✅ Add a tool node Why? A tool node is used when the topic author wants to explicitly tell the topic: ✅ Add a tool node Why? A connector action can be exposed as a tool, and a tool node lets you invoke that action from the topic.
  3. Arcadiuz 👍 1
    - Enable generative orchestration - Add a tool node - Add a tool node Generative orchestration allows the agent to decide which available tool to invoke based on the user's request and the tool descriptions. A tool node allows a topic to invoke a specific tool or action at a defined point in the conversation. This is useful when the workflow must execute a particular operation at a predictable point. Why the other options are wrong -Adaptive Card: Collects structured user input; it does not orchestrate tools. -Static message: Displays information but does not execute a tool. -Question node: Collects user input but does not replace tool invocation.

Reader comments & corrections

No reader corrections yet — spotted an error or have a note? Share it below.

Log in to comment, report an error, or add a note about this question.

← Back to AB-620 Study Guide