Level 200: Practitioner

This article provides insights for Product Managers (PMs) working on AI features, emphasizing the importance of understanding user needs and business value. It highlights the practical approach to learning AI through user-centric lenses and the significance of asking questions when faced with new challenges.

This code snippet demonstrates how to use agent operations with the Sharepoint tool from the Azure Agents service using a synchronous client. It creates an agent, initializes a Sharepoint tool with a connection ID, and interacts with agents and threads for communication. The code provides a practical implementation of agent orchestration and tool integration within an AI project environment.

This code snippet demonstrates how to use agent operations with a toolset from the Azure Agents service using a synchronous client. It showcases creating an agent with a toolset, enabling auto function calls, creating threads for communication, and sending messages within an agent system.

This code snippet demonstrates how to use agent operations with the OpenAPI tool from the Azure Agents service using custom key authentication against the TripAdvisor API. It showcases setting up connections, loading OpenAPI specs, and initializing an Agent OpenAPI tool. This code provides practical implementation examples for integrating Azure AI services with external APIs.

This code snippet demonstrates how to use the Azure Agents service with OpenAPI tools for agent operations using a synchronous client. It showcases setting up authentication, initializing agent tools with OpenAPI specs, and creating an agent to retrieve weather information and a list of countries. The code provides hands-on experience in integrating Azure AI services and working with OpenAPI specifications.

This code snippet demonstrates how to use agent operations with multiple Model Context Protocol (MCP) servers from the Azure Agents service using a synchronous client. It showcases how to interact with AI models deployed on different MCP servers and manage tools dynamically within the agents.

This code snippet demonstrates how to use Azure Agents service with the Connected Agent tool in Python. It shows how to create multiple agents, such as 'stock_price_bot' and 'weather_bot', and provides instructions for setting up the environment variables and dependencies before running the sample.

This code snippet demonstrates how to use agent operations with the Model Context Protocol (MCP) tool from the Azure Agents service using a synchronous client. It provides a practical example of creating an agent with MCP tool and processing agent runs within an Azure AI project environment.

This code snippet demonstrates how to use agents with Logic Apps to execute the task of sending an email. It provides a sample implementation using Azure AI agents and Logic Apps, along with instructions on prerequisites and usage.

This code snippet demonstrates how to use agent operations with custom functions from the Azure Agents service using a synchronous client. It showcases creating an agent, running user requests with function calls, creating threads, messages, and runs, and monitoring the status of the run.

This code snippet demonstrates how to use agent operations with file searching from the Azure Agents service using a synchronous client. It showcases uploading a file, creating a vector store, and creating an agent with a file search tool, providing hands-on experience with Azure AI Projects and Agents SDK.

This code snippet demonstrates how to use Agent operations with the Microsoft Fabric grounding tool from the Azure Agents service using a synchronous client. It showcases creating an agent, initializing a Fabric tool, creating threads for communication, and processing an Agent run with tools.

This code snippet demonstrates how to add files to an agent during the vector store creation using Azure AI tools. It involves setting up the necessary environment variables, creating a vector store, and utilizing Azure services for data storage and retrieval.

This code snippet demonstrates how to use Azure Agents service with the Deep Research tool through a Python client. It includes functions for converting citation markers in markdown content to HTML superscript format. The sample provides practical guidance on integrating Azure AI services and processing text data.

This code snippet demonstrates how to use the Connected Agent tool from the Azure Agents service to create agents for specific tasks like getting stock prices. It showcases the integration of AI models and agents for building conversational AI systems.

This code snippet demonstrates how to use agent operations with a code interpreter from the Azure Agents service using a synchronous client. It showcases creating an agent, creating a thread, and uploading a local file to Azure for vector store creation.

This code snippet demonstrates how to use agent operations with a code interpreter from the Azure Agents service using a synchronous client. It showcases uploading a file, creating an agent with a code interpreter tool, and creating a message thread within an AI project environment.

This code snippet demonstrates how to use the Azure Agents service with the Browser Automation tool for browser automation tasks. It shows how to create a new agent with the Browser Automation tool attached, enabling the agent to perform tasks related to web browsing.

This code snippet demonstrates how to create an agent using the Bing grounding tool from the Azure Agents service. It showcases the integration of the Azure AI Project client, agent creation with specific tools, and message handling within a thread, providing insights into building AI agents with specialized functionalities.

This code snippet demonstrates how to use the Azure Agents service with the Bing Custom Search tool to create an agent for performing search operations. It showcases the integration of Azure AI tools for agent orchestration and communication.

This code snippet demonstrates how to use Azure Function agent operations from the Azure Agents service using a synchronous client. It showcases setting up an Azure Function tool to interact with a bot and provides guidance on required environment variables and dependencies. The learning value includes understanding how to integrate Azure Functions with AI agents for automated tasks.

This code snippet demonstrates how to use agent operations with Azure AI Search tool from the Azure agents service using a synchronous client. It provides a practical example of setting up an agent with Azure AI Search capabilities and initializing the AzureAISearchTool for performing search operations.

This code snippet demonstrates how to enable automatic function calls in Azure AI agents using Python. It shows how to create an agent, set up functions to be called automatically, and initialize the agent for use in AI projects. The code provides a practical example for integrating AI agents with custom functions.

This repository provides a pre-built LangGraph tools agent for the Open Agent Platform, enabling users to work with MCP servers and a LangConnect RAG tool. It includes setup instructions and integration details with the Open Agent Platform, making it a valuable resource for developers interested in agent orchestration and tooling automation.

The video provides a concise overview of Google Agentspace, explaining its functionality and purpose. It offers a quick insight into building AI agents on Google Cloud, making it a valuable resource for AI developers interested in multi-agent systems and cloud-based AI development.

The article delves into the fundamentals and best practices of AI governance, emphasizing the need for a robust framework to manage AI risks and ensure data protection. It provides insights for AI developers and builders on implementing governance strategies to address security threats and compliance requirements.

The AI for Beginners curriculum by Microsoft offers a comprehensive 12-week program with 24 lessons covering practical AI concepts, quizzes, and labs. This resource is ideal for AI developers and builders looking to start their journey in artificial intelligence.

This article serves as a comprehensive guide for individuals looking to learn AI from scratch in 2025, offering insights from industry experts, practical advice, and tips on mastering AI skills and tools. It emphasizes the increasing relevance of AI in various industries and provides a roadmap for aspiring data scientists, machine learning engineers, AI researchers, and enthusiasts.

This YouTube video discusses the basics of AI for beginners, focusing on key takeaways from Google's AI Essentials course. The presenter covers topics such as types of AI tools, implied context, zero-shot vs. few-shot prompting, chain-of-thought prompting, and the limitations of AI, providing insights into the pros and cons of the certification course.

This article discusses the process of handling unstructured data using Snowflake Cortex AI for geocoding and geofencing tasks. It provides insights into breaking down complex data problems, utilizing marketplace apps for geocoding services, and scaling up data processing for large datasets.

This article from MIT Sloan Teaching & Learning Technologies provides beginner-friendly resources on key AI concepts like neural networks, natural language processing, and model architectures. It offers insights into generative AI foundations for teaching and practical tips on writing effective prompts and mitigating bias in AI tools.

This article clarifies the distinction between AI and machine learning, highlighting how machine learning is a subset of AI that focuses on training algorithms to learn from data. It provides insights into popular terms like neural networks, deep learning, and large language models, offering a foundational understanding of how these concepts interrelate.