🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901 aws-aif-c01
Guided AB-620 Domain 1
Domain 1 — Module 6 of 10 60%
6 of 28 overall

AB-620 Study Guide

Domain 1: Plan and Configure Agent Solutions

  • Getting Started: Copilot Studio for Developers Free
  • Planning Enterprise Integration and Reusable Components Free
  • Identity Strategy for Agents Free
  • Channels, Deployment and Audience Design Free
  • Responsible AI and Security Governance Free
  • Agent Flows: Build, Monitor and Handle Errors Free
  • Human-in-the-Loop Agent Flows Free
  • Topics, Tools and Variables Free
  • Advanced Responses: Custom Prompts and Generative Answers Free
  • API Calls, HTTP Requests and Adaptive Cards Free

Domain 2: Integrate and Extend Agents in Copilot Studio

  • Enterprise Knowledge Sources: The Big Picture
  • Copilot Connectors and Power Platform Connectors
  • Azure AI Search as a Knowledge Source
  • Adding Tools: Custom Connectors and REST APIs
  • MCP Tools: Model Context Protocol in Action
  • Computer Use: Agent-Driven UI Automation
  • Multi-Agent Solutions: Design and Agent Reuse
  • Integrating Foundry Agents
  • Fabric Data Agents: Analytics Meets AI
  • A2A Protocol: Cross-Platform Agent Collaboration
  • Grounded Answers: Azure AI Search with Foundry
  • Foundry Model Catalog and Application Insights

Domain 3: Test and Manage Agents

  • Test Sets & Evaluation Methods
  • Reviewing Results & Tuning Performance
  • Solutions & Environment Variables
  • Power Platform Pipelines for Agent ALM
  • Agent Lifecycle: From Dev to Production
  • Exam Prep: Diagnostic Review

AB-620 Study Guide

Domain 1: Plan and Configure Agent Solutions

  • Getting Started: Copilot Studio for Developers Free
  • Planning Enterprise Integration and Reusable Components Free
  • Identity Strategy for Agents Free
  • Channels, Deployment and Audience Design Free
  • Responsible AI and Security Governance Free
  • Agent Flows: Build, Monitor and Handle Errors Free
  • Human-in-the-Loop Agent Flows Free
  • Topics, Tools and Variables Free
  • Advanced Responses: Custom Prompts and Generative Answers Free
  • API Calls, HTTP Requests and Adaptive Cards Free

Domain 2: Integrate and Extend Agents in Copilot Studio

  • Enterprise Knowledge Sources: The Big Picture
  • Copilot Connectors and Power Platform Connectors
  • Azure AI Search as a Knowledge Source
  • Adding Tools: Custom Connectors and REST APIs
  • MCP Tools: Model Context Protocol in Action
  • Computer Use: Agent-Driven UI Automation
  • Multi-Agent Solutions: Design and Agent Reuse
  • Integrating Foundry Agents
  • Fabric Data Agents: Analytics Meets AI
  • A2A Protocol: Cross-Platform Agent Collaboration
  • Grounded Answers: Azure AI Search with Foundry
  • Foundry Model Catalog and Application Insights

Domain 3: Test and Manage Agents

  • Test Sets & Evaluation Methods
  • Reviewing Results & Tuning Performance
  • Solutions & Environment Variables
  • Power Platform Pipelines for Agent ALM
  • Agent Lifecycle: From Dev to Production
  • Exam Prep: Diagnostic Review
Domain 1: Plan and Configure Agent Solutions Free ⏱ ~15 min read

Agent Flows: Build, Monitor and Handle Errors

Create Power Automate cloud flows for Copilot Studio agents with input/output parameters, monitoring, and error handling patterns.

What Are Agent Flows?

☕ Simple explanation

Think of your agent as a hotel concierge. The concierge can answer questions and make small talk, but when a guest asks to book a restaurant, they pick up the phone and call the restaurant. That phone call is the agent flow.

Agent flows are Power Automate cloud flows that your Copilot Studio agent “calls” when it needs to do real work — look up data, create records, send emails, or talk to external systems. The agent handles the conversation; the flow handles the action.

Agent flows are Power Automate cloud flows invoked from Copilot Studio topics. They extend agent capabilities beyond conversation into transactional operations — CRUD against Dataverse, calls to external APIs, complex business logic, and multi-step orchestration.

Key architectural points:

  1. Trigger: Every agent flow uses exactly one trigger — “When an agent calls a flow” (previously “Run a flow from Copilot”). No other trigger type works for agent invocation.
  2. Execution model: Agent flows run synchronously from the agent’s perspective. The topic pauses, the flow executes, and the topic resumes with the flow’s output.
  3. Scope: Flows run in the context of the agent’s connection identity, not the end user’s identity. Service principal or connection reference applies.

The Only Trigger That Works

Every agent flow starts with the same trigger: “When an agent calls a flow.” This is non-negotiable — you cannot use “When an HTTP request is received,” scheduled triggers, or Dataverse triggers for agent-invoked flows. This trigger is what registers the flow in Copilot Studio’s action picker.

When you create a new cloud flow from within Copilot Studio, this trigger is added automatically. If you build the flow in Power Automate first, you must manually select this trigger or the flow will not appear in the agent’s action list.

Input and Output Parameters

Agent flows communicate with topics through typed parameters.

Input parameters are defined on the trigger. Each input has a name, type (Text, Number, Boolean, Object, Array), and an optional description. When the topic calls the flow, it maps topic variables to these inputs.

Output parameters are defined on the “Return value(s) to the agent” action at the end of the flow. Every production flow should return at least two outputs:

OutputTypePurpose
successBooleanDid the flow complete its intended task?
errorMessageTextEmpty on success, descriptive message on failure
resultText or ObjectThe actual data the agent needs to continue the conversation

This pattern lets your topic branch on success or failure and give the user a meaningful response instead of a generic error.

💡 Why always return success and errorMessage?

Without a success flag, the topic has no way to know if the flow failed silently. The agent would continue as if everything worked — presenting empty data or worse, incorrect data.

Returning an errorMessage lets you surface a specific, helpful message like “Could not retrieve shipment status because the carrier API is unavailable” instead of “Something went wrong.”

Exam questions often test whether you know to include explicit error signalling in flow outputs, not just the happy-path data.

Configuring Actions and Connectors

Inside an agent flow you use the same Power Automate actions and connectors as any cloud flow — Dataverse (CRUD), HTTP (external APIs), Office 365 (email, Teams), custom connectors (OpenAPI), and AI Builder (document extraction, classification).

The key difference: agent flows must complete quickly. The conversation pauses while the flow runs, so avoid long-running operations like bulk processing. Keep each flow focused on a single responsibility.

Monitoring Agent Flows

When something goes wrong — and it will — you need to know where to look.

Four monitoring surfaces for agent flows
FeaturePA Run HistoryCS AnalyticsApplication InsightsDataverse Audit Log
What it showsIndividual flow run status, inputs, outputs, step-by-step executionConversation-level metrics — resolution rate, escalation rate, topic usageCustom telemetry, latency, error rates, dependency trackingWho changed what in Dataverse tables and when
Best forDebugging a specific failed flow runUnderstanding overall agent effectivenessProduction performance monitoring and alertingCompliance and change tracking
GranularityPer-run, per-action detailAggregated across sessionsPer-request with custom dimensionsPer-record, per-field changes
Setup requiredNone — built inNone — built inMust configure connection in Copilot Studio settingsEnable auditing in Power Platform admin centre
LatencyNear real-timeUp to 1 hour delayNear real-time with streamingNear real-time

Error Handling Patterns

Robust agent flows anticipate failure. Five error handling patterns are available in Power Automate, and the exam expects you to know when to use each one.

Five error handling patterns for agent flows
FeatureTry/Catch (Scope)Retry PolicyParallel BranchTerminateError Output
How it worksWrap actions in a Scope; configure a second Scope to run on failureSet retry count and interval on individual actionsRun a fallback path alongside the primary pathStop the flow immediately with Failed statusReturn error details through the flow's output parameters
Best forCatching any failure in a group of actionsTransient errors — 429 throttling, network timeoutsProviding an alternative data source or fallback logicUnrecoverable errors where continuing would cause harmLetting the agent topic decide how to handle the failure
User experienceAgent can continue with fallback responseUser waits slightly longer but gets a resultUser is unaware — fastest alternative winsAgent receives failure and must handle gracefullyAgent shows a contextual error message to the user
Exam signalQuestion mentions grouping multiple stepsQuestion mentions 429, throttling, or intermittentQuestion mentions fallback or alternative sourceQuestion mentions stop immediately or prevent damageQuestion mentions return error to agent or meaningful message
💡 Exam tip: Agent flows must be synchronous

This is frequently tested. Agent flows execute synchronously — the conversation pauses until the flow completes. You cannot use async patterns like queues or webhooks within the agent flow.

For long-running operations: start the operation, return an acknowledgement, and notify the user separately when it completes.

🚚 Dev Debugs a 429 Throttling Error

Dev is building a delivery tracking agent for his logistics company. The agent calls a flow that queries a third-party carrier API to get shipment status. During peak hours the carrier API starts returning HTTP 429 (Too Many Requests) errors and customers see “I couldn’t retrieve your shipment status” messages.

Step 1: Dev opens Power Automate run history and finds the failed runs. The HTTP action shows a 429 response with a Retry-After: 30 header.

Step 2: He configures a retry policy on the HTTP action — exponential interval, 3 retries, minimum interval of 30 seconds. This handles the transient throttling automatically.

Step 3: He wraps the HTTP call in a Scope (try/catch). If all retries fail, the catch Scope sets success = false and errorMessage = "The carrier system is busy. Please try again in a few minutes." The agent now gives customers a specific, helpful message instead of a generic error.

Step 4: He checks Application Insights and finds throttling spikes between 2–4 PM — the carrier’s batch processing window.

Key Terms

Question

What is the only valid trigger for an agent flow in Copilot Studio?

Click or press Enter to reveal answer

Answer

'When an agent calls a flow' (previously 'Run a flow from Copilot'). No other trigger type — HTTP, scheduled, Dataverse — will make the flow available to the agent. This trigger registers the flow in the agent's action picker.

Click to flip back

Question

Why should every agent flow return both a success boolean and an errorMessage string?

Click or press Enter to reveal answer

Answer

Without a success flag the topic cannot distinguish between a successful operation and a silent failure. The errorMessage provides context so the agent can give users a specific, helpful response. This pattern enables proper branching in the topic's conversation flow.

Click to flip back

Question

What is the execution model for agent flows?

Click or press Enter to reveal answer

Answer

Synchronous. The conversation topic pauses while the flow executes, then resumes when the flow returns its output values. The agent cannot fire-and-forget a flow or receive streaming partial results during execution.

Click to flip back

Question

What are the four monitoring surfaces for agent flows?

Click or press Enter to reveal answer

Answer

1) Power Automate run history — per-run debugging. 2) Copilot Studio analytics — conversation-level metrics. 3) Application Insights — production telemetry and alerting (requires configuration). 4) Dataverse audit log — compliance and change tracking.

Click to flip back

Knowledge Check

Knowledge Check

Dev's delivery tracking flow calls an external carrier API that intermittently returns HTTP 429 errors during peak hours. What is the most appropriate error handling pattern?

Knowledge Check

Priya at AgentForge is building an ISV agent that calls a flow to create records in a customer's Dataverse. The flow must return data to the agent topic. Which trigger should she use?

Knowledge Check

An agent flow calls three Dataverse actions in sequence: create a case, create a task, and send a notification. If the task creation fails, the flow should skip the notification but still return an error message. What pattern should you use?


🎬 Video coming soon

Agent Flows: Build, Monitor and Handle Errors

Next up: Human-in-the-Loop Agent Flows — approval workflows, live agent transfers, and escalation patterns that keep humans in control when it matters.

← Previous

Responsible AI and Security Governance

Next →

Human-in-the-Loop Agent Flows

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.