Picture by Writer | Canva & ChatGPT
# Introduction
GitHub has change into the go-to platform for freshmen desirous to be taught new programming languages, ideas, and abilities. With the rising curiosity in agentic AI, the platform is more and more showcasing actual initiatives that concentrate on “agentic workflows,” making it a perfect atmosphere to be taught and construct.
One notable useful resource is microsoft/ai-agents-for-beginners, which includes a 12-lesson course overlaying the basics of constructing AI brokers. Every lesson is designed to face by itself, permitting you to start out at any level that fits your wants. This repository additionally affords multi-language assist, guaranteeing broader accessibility for learners. Every lesson on this course contains code examples, which will be discovered within the code_samples folder.
Furthermore, this course makes use of Azure AI Foundry and GitHub Mannequin Catalogs for interacting with language fashions. It additionally incorporates a number of AI agent frameworks and companies like Azure AI Agent Service, Semantic Kernel, and AutoGen.
To facilitate your decision-making course of and supply a transparent overview of what you’ll be taught, we’ll assessment every lesson intimately. This information serves as a useful useful resource for freshmen who would possibly really feel unsure about selecting a place to begin.
# 1. Intro to AI Brokers and Agent Use Instances
This lesson introduces AI brokers — programs powered by massive language fashions (LLMs) that sense their atmosphere, motive over instruments and information, and act — and surveys key agent varieties (easy/model-based reflex, objective/utility-based, studying, hierarchical, and multi-agent programs (MAS)) by way of travel-booking examples.
You’ll be taught when to use brokers to open-ended, multi-step, and improvable duties, and the foundational constructing blocks of agentic options: defining instruments, actions, and behaviors.
# 2. Exploring AI Agentic Frameworks
This lesson explores AI agent frameworks with pre-built parts and abstractions that allow you to prototype, iterate, and deploy brokers sooner by standardizing widespread challenges and boosting scalability and developer effectivity.
You’ll evaluate Microsoft AutoGen, Semantic Kernel, and the managed Azure AI Agent Service, and be taught when to combine along with your current Azure ecosystem versus utilizing standalone instruments.
# 3. Understanding AI Agentic Design Patterns
This lesson introduces AI agentic design rules, a human-centric consumer expertise (UX) strategy for constructing customer-focused agent experiences amid the inherent ambiguity of generative AI.
You’ll be taught what the rules are, sensible pointers for making use of them, and examples of their use, with an emphasis on brokers that broaden and scale human capacities, fill information gaps, facilitate collaboration, and assist individuals change into higher variations of themselves by way of supportive, goal-aligned interactions.
# 4. Software Use Design Sample
This lesson introduces the tool-use design sample, which permits LLM-powered brokers to have managed entry to exterior instruments akin to features and APIs, enabling them to take actions past simply producing textual content.
You’ll study key use circumstances, together with dynamic knowledge retrieval, code execution, workflow automation, buyer assist integrations, and content material era/enhancing. Moreover, the lesson will cowl the important constructing blocks of this design sample, akin to well-defined software schemas, routing and choice logic, execution sandboxing, reminiscence and observations, and error dealing with (together with timeout and retry mechanisms).
# 5. Agentic RAG
This lesson explains agentic retrieval-augmented era (RAG), a multi-step retrieval-and-reasoning strategy pushed by massive language fashions (LLMs). On this strategy, the mannequin plans actions, alternates between software/operate calls and structured outputs, evaluates outcomes, refines queries, and repeats the method till reaching a passable reply. It typically makes use of a maker-checker loop to reinforce correctness and recuperate from malformed queries.
You’ll be taught concerning the conditions the place agentic RAG excels, notably in correctness-first situations and prolonged tool-integrated workflows, akin to API calls. Moreover, you’ll uncover how taking possession of the reasoning course of and utilizing iterative loops can improve reliability and outcomes.
# 6. Constructing Reliable AI Brokers
This lesson teaches you how you can construct reliable AI brokers by designing a strong system message framework (meta prompts, fundamental prompts, and iterative refinement), imposing safety and privateness finest practices, and delivering a high quality consumer expertise.
You’ll be taught to determine and mitigate dangers, akin to immediate/objective injection, unauthorized system entry, service overloading, knowledge-base poisoning, and cascading errors.
# 7. Planning Design Sample
This lesson focuses on planning design for AI brokers. Begin by defining a transparent general objective and establishing success standards. Then, break down complicated duties into ordered and manageable subtasks.
Use structured output codecs to make sure dependable, machine-readable responses, and implement event-driven orchestration to deal with dynamic duties and surprising inputs. Equip brokers with the suitable instruments and pointers for when and how you can use them.
Constantly consider the outcomes of the subtasks, measure efficiency, and iterate to enhance the ultimate outcomes.
# 8. Multi-Agent Design Sample
This lesson explains the multi-agent design sample, which entails coordinating a number of specialised brokers to collaborate towards a shared objective. This strategy is especially efficient for complicated, cross-domain, or parallelizable duties that profit from the division of labor and coordinated handoffs.
On this lesson, you’ll be taught concerning the core constructing blocks of this design sample: an orchestrator/controller, role-defined brokers, shared reminiscence/state, communication protocols, and routing/hand-off methods, together with sequential, concurrent, and group chat patterns.
# 9. Metacognition Design Sample
This lesson introduces metacognition, which will be understood as “interested by pondering,” for AI brokers. Metacognition permits these brokers to watch their very own reasoning processes, clarify their choices, and adapt primarily based on suggestions and previous experiences.
You’ll be taught planning and analysis strategies, akin to reflection, critique, and maker-checker patterns. These strategies promote self-correction, assist determine errors, and stop limitless reasoning loops. Moreover, these strategies will improve transparency, enhance the standard of reasoning, and assist higher adaptation and notion.
# 10. AI Brokers in Manufacturing
This lesson demonstrates how you can remodel “black field” brokers into “glass field” programs by implementing strong observability and analysis strategies. You’ll mannequin runs as traces (representing end-to-end duties) and spans (petitions for particular steps involving language fashions or instruments) utilizing platforms like Langfuse and Azure AI Foundry. This strategy will allow you to carry out debugging and root-cause evaluation, handle latency and prices, and conduct belief, security, and compliance audits.
You’ll be taught what points to guage, akin to output high quality, security, tool-call success, latency, and prices, and apply methods to reinforce efficiency and effectiveness.
# 11. Utilizing Agentic Protocols
This lesson introduces agentic protocols that standardize the methods AI brokers join and collaborate. We are going to discover three key protocols:
Mannequin Context Protocol (MCP), which offers constant, client-server entry to instruments, sources, and prompts, functioning as a “common adapter” for context and capabilities.
Agent-to-Agent Protocol (A2A), which ensures safe, interoperable communication and job delegation between brokers, complementing the MCP.
Pure Language Internet Protocol (NLWeb), which permits natural-language interfaces for web sites, permitting brokers to find and work together with internet content material.
On this lesson, you’ll be taught concerning the objective and advantages of every protocol, how they allow massive language fashions (LLMs) to speak with instruments and different brokers, and the place every suits into bigger architectures.
# 12. Context Engineering for AI Brokers
This lesson introduces context engineering, which is the disciplined observe of offering brokers with the correct info, in the correct format, and on the proper time. This strategy permits them to plan their subsequent steps successfully, shifting past one-time immediate writing.
You’ll find out how context engineering differs from immediate engineering, because it entails ongoing, dynamic curation slightly than static directions. Moreover, you’ll perceive why methods akin to writing, choosing, compressing, and isolating info are important for reliability, particularly given the constraints of constrained context home windows.
# Closing Ideas
This GitHub course offers all the things you should begin constructing AI brokers. It contains complete classes, brief movies, and runnable Python code. You’ll be able to discover subjects in any order and run samples utilizing GitHub Fashions (obtainable free of charge) or Azure AI Foundry.
Moreover, you’ll have the chance to work with Microsoft’s Azure AI Agent Service, Semantic Kernel, and AutoGen. This course is community-driven and open supply; contributions are welcome, points are inspired, and it’s licensed so that you can fork and prolong.
Abid Ali Awan (@1abidaliawan) is a licensed knowledge scientist skilled who loves constructing machine studying fashions. Presently, he’s specializing in content material creation and writing technical blogs on machine studying and knowledge science applied sciences. Abid holds a Grasp’s diploma in expertise administration and a bachelor’s diploma in telecommunication engineering. His imaginative and prescient is to construct an AI product utilizing a graph neural community for college kids fighting psychological sickness.
