CertifyDeckCargando contenido…
The official Microsoft Certified: AI Agent Builder Associate syllabus, organized by domain. Check off each point as you review it.
Inicia sesión para guardar tu progreso entre sesiones.
Plan an agent solution
Design how the agent connects to enterprise systems, selecting connectors, APIs, flows, or other patterns based on security, latency, and maintainability.
Define authentication, authorization, and user or author identity so every interaction applies appropriate permissions and least privilege.
Choose channels and deployment environments based on audience, authentication, supported capabilities, governance, and publishing lifecycle.
Plan responsible AI controls for safety, transparency, privacy, human oversight, usage boundaries, and continuous agent evaluation.
Assess security and governance risks, including data policies, permissions, information exposure, connectors, and channel publishing.
Identify topics, flows, prompts, tools, and specialist agents that can be designed as reusable, governed components.
Adapt identity, data, channels, tone, and security for agents intended for authenticated employees or external users.
Create and monitor agent flows in Copilot Studio
Create an agent flow with well-defined triggers, inputs, logic, actions, and outputs to automate deterministic processes.
Add human approval or intervention at high-impact decision points, exceptions, or actions that require review.
Configure actions and connectors with clear contracts, valid connections, appropriate authentication, and parameters the agent can use reliably.
Monitor flow runs, duration, errors, and dependencies to detect failures, bottlenecks, and operational regressions.
Define input and output parameters with unambiguous names, types, and descriptions to exchange data correctly between agent and flow.
Implement error handling, timeouts, retries, fallback paths, and useful messages so failures are safe and diagnosable.
Configure topics
Add an agent flow to a topic, map its inputs and outputs, and use the results in later conversation steps.
Format agent responses using text, lists, tables, variables, or structures appropriate to the channel and user need.
Add tools within a topic and configure when they run, what data they receive, and how their results are processed.
Create custom prompts with appropriate instructions, inputs, outputs, model, and testing to produce advanced, consistent responses.
Integrate custom knowledge sources and transform results into the expected format to ground controlled generative answers.
Call APIs from topics with HTTP requests by configuring URL, method, headers, body, authentication, response, and error handling.
Configure a generative answers node, its sources, variables, and boundaries to produce grounded responses at the appropriate point in a topic.
Design valid adaptive cards to present information and collect input in a structured format supported by the channel.
Manage topic, global, and system variables, including scope, types, initial values, and data transfer between nodes.