Program
Agent behavior coordination using Generative AI
Agents can use either generative or classical scheduling. By default, newly created agents will use generative scheduling.
Latest Program Articles Page 3
Program
Template agent Safe Travels
An agent built from the Safe Travels agent template is a business-to-employee (B2E) agent designed to provide travel support for a company's employees.
Program
Template agent IT Helpdesk
An agent built from an IT Helpdesk agent template uses your organization's knowledge base to improve operational efficiency, enhance employee satisfaction, and optimize resource utilization in technical support scenarios.
Program
Template agent Citizen Services
An agent built from the Citizen Services agent platform allows public sector organizations to quickly build agents using their publicly available information to help citizens navigate government services and information through a question-and-answer-like experience.
Program
Template agent Financial Insights
An agent built from the Financial Insights agent template allows users to build their own agents within Copilot Studio, and is designed for financial services professionals.
Program
Install managed agents from Microsoft.
Microsoft provides a catalog of managed agents that you can browse and install directly in Copilot Studio.
Program
Create a custom agent from the agent template.
To help you get started building custom agents, Microsoft Copilot Studio provides several agent templates that you can use to create your own custom agents.
Program
How to use Cursor Rules File (.mdc)
This guide explains how to create and use Cursor Rules (.mdc) with the YAML frontmatter, including 4 activation modes and how to apply AI rules to an entire project.
Program
How to create an English review conversation on Educaplay
Educaplay is a powerful online platform that allows teachers to design interactive dialogues. Through themed dialogues, students have the opportunity to review lessons.
Program
Running DeepSeek V4-Pro in Claude Code
Running DeepSeek V4-Pro inside Claude Code at only 1/7 the cost of Opus. 8 lessons covered configuring 4 environment variables, the issue with the suffix [1m], cost calculation, sub-agent routing, and an honest decision tree on when V4-Pro outperformed Opus.
Program
Change the details of the test kit.
This article explains how to modify the name and settings of the test suite, manage user profiles and connections used for validation, edit or remove individual test cases, and delete the entire test suite or results.
Program
Edit test cases in the test toolkit.
During or after creating the test suite, you can edit test cases by changing the question wording or modifying expected answers, keywords, or tools as needed.
Program
Choose a method for evaluating agents.
When creating a test suite, choose from different testing methods to evaluate agent responses. Each testing method has its own advantages and is suitable for different types of assessments.
Program
Run the test and view the agent evaluation results.
Run reviews and analyze the results to optimize agent behavior and confirm that the agent meets your quality and business requirements.
Program
Automate agent evaluation using the Power Platform API.
Copilot Studio provides users with tools to continuously evaluate agent performance by running automated tests based on predefined test suites using the Power Platform REST API.
Program
Check the Copilot Studio agent.
When designing agents in Copilot Studio, use test cases to see how the agent guides the customer through the conversation. This is a good way to ensure the topics work and the conversation unfolds as you expect.
Program
Overview of agent evaluation
As AI agents take on a critical role in business processes, the need for reliable and repeatable testing becomes essential. Agent evaluation allows you to create tests that simulate real-world scenarios for your agents.
Program
Create a single response test suite.
Evaluating individual responses is very useful when you want to test your agents on how they answer specific questions, on the functions they call, and on the precise wording they use in their responses.
Program
Use entities and fill in the blanks in the agent.
A crucial part of agent conversations in Copilot Studio is natural language comprehension, that is, the ability of the AI to understand user intent.
Program
Ensure compliance with Copilot Studio's regulations.
In today's digital landscape, regulatory compliance is more important than ever. Organizations must adhere to numerous regulations and standards to protect sensitive data, maintain customer trust, and avoid legal consequences.