#developer

Developer tutorial on what you need to run the code in Microsoft's AI Agents for Beginners course: forking the repo, Python 3.12, the Azure CLI, a Foundry project with a deployed model, and how to avoid common stumbling blocks.

A developer deep-dive: why use an agent framework, what work it saves you, and what Microsoft's Agent Framework and Foundry Agent Service each handle.

Developer advanced tutorial: designing agents from the user experience, with ideas at three levels (space, time, core), then down to three practical guidelines: transparent, controllable, consistent.

Developer advanced tutorial: how function calling lets large models use tools, the three things you need to prepare, and what to watch for with errors, state and security when using tools.

Developer advanced tutorial: to build a trustworthy agent, manage its system prompt well and recognize six common threats: tampered instructions, unauthorized access, resource abuse, knowledge base poisoning, cascading failures, and how to defend against them.

Advanced developer tutorial: how to get an Agent to handle complex tasks: set the goal first, split it into subtasks, use structured output (JSON) so downstream steps can pick it up easily, then use event-driven handling for unexpected situations.

An advanced developer tutorial on when to use multiple agents, what they offer over a single agent, and communication and collaboration patterns (group chat, hand-off) and how to see what they are doing.

Developer advanced tutorial: once an agent is live, you need visibility into it. Use traces and spans to record the process, monitor latency, cost, errors, user feedback and accuracy, and run automated evaluations.

Developer deep dive: how the three agent protocols divide the work. MCP lets models connect to tools and data, A2A lets different agents collaborate with each other, and NLWeb lets websites be accessed in natural language.

Advanced developer tutorial: what Microsoft's Agent Framework offers: five multi-agent orchestration patterns, observability, security, durability and human-in-the-loop approval, plus core concepts such as agents, tools and conversation threads.

An advanced developer tutorial: how browser agents read pages, click buttons and extract data; when to use an agent approach versus precise control; and the safety guardrails to set up before going live.

Developer advanced tutorial: the difference between prototype and production-grade agents, three deployment approaches, the lifecycle, and what to add for scaling, observability, cost, and enterprise governance.

Advanced developer tutorial: running agents with small models on your own computer, the three benefits of privacy, cost savings and offline use, what small models are good and bad at, and how to pair local tools, retrieval and MCP.

Advanced developer tutorial: Agent logs can be altered, so what can you use to prove integrity during an audit? Use signed receipts to record each tool call, hash chains to prevent deletion and tampering, and clarify what they can and cannot prove.