[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-92283":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":10,"languages":10,"totalLinesOfCode":10,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":14,"stars7d":14,"stars30d":15,"stars90d":14,"forks30d":14,"starsTrendScore":14,"compositeScore":16,"rankGlobal":10,"rankLanguage":10,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":14,"starSnapshotCount":14,"syncStatus":15,"lastSyncTime":34,"discoverSource":35},92283,"ai-agents-tutorial","amitshekhariitbhu\u002Fai-agents-tutorial","amitshekhariitbhu","Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.","https:\u002F\u002Foutcomeschool.com\u002Fprogram\u002Fai-and-machine-learning",null,105,31,101,0,2,44.72,"Apache License 2.0",false,"main",true,[22,23,24,25,26,27,28,29,30],"agent-evaluation","agent-loop","agent-orchestration","ai-agent","ai-agent-tutorial","ai-agents","harness-engineering","multi-agent-systems","tool-calling-agent","2026-07-22 04:02:05","\u003Cp align=\"center\">\n    \u003Cimg alt=\"AI Agents Tutorial\" src=\"https:\u002F\u002Fgithub.com\u002Famitshekhariitbhu\u002Fai-agents-tutorial\u002Fblob\u002Fmain\u002Fassets\u002Fbanner.png\">\n\u003C\u002Fp>\n\n# AI Agents Tutorial\n\n**Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.**\n\n---\n\nPrepared and maintained by the **Founder** of Outcome School: [Amit Shekhar](https:\u002F\u002Fx.com\u002Famitiitbhu)\n\n---\n\n**Note: This series will continue to grow as I write more blogs and create more videos on new topics. Keep learning.**\n\n---\n\n## AI Engineering (LLM, RAG, MCP, Agent)\n\nBefore diving into AI Agents, it's a good idea to first understand the foundations that agents are built on.\n\nIn this video, we will cover the following:\n\n* LLM\n* RAG\n* MCP\n* Agent\n* Fine-tuning\n* Quantization\n\nLet's get started: [AI Engineering Explained: LLM, RAG, MCP, Agent, Fine-Tuning, Quantization](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=lnfWvX66FUk)\n\n---\n\n## AI Agent Explained\n\nIn this blog, we will learn about the AI Agent - what it is, how it is different from a plain LLM, its five core parts, how it works end to end, the main types, and when to use one.\n\nWe will cover the following:\n\n- The Big Picture\n- What is an AI Agent\n- AI Agent vs Plain LLM vs Chatbot\n- The Five Core Parts\n- How an AI Agent Works End to End\n- A Concrete Example: Research Agent\n- Types of AI Agents\n- What AI Agents Can Do Today\n- When to Use an AI Agent\n- Common Failure Modes\n- Quick Summary\n\nLet's get started: [AI Agent Explained](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-agent)\n\n---\n\n## How does Function Calling work in LLMs?\n\nIn this blog, we will learn about how Function Calling works in LLMs. We will see what it is, why we need it, the key insight behind it, and how it powers AI agents and assistants step by step.\n\nWe will cover the following:\n\n- What is Function Calling\n- Why We Need Function Calling\n- The Key Insight: The Model Does Not Run the Function\n- How Function Calling Works Step by Step\n- A Concrete Example: get_weather(city)\n- The Conversation Loop\n- Multi-Step and Parallel Function Calling\n- Relation to Structured Outputs and JSON Mode\n- Real-World Use: The Backbone of AI Agents\n- Quick Summary\n\nLet's get started: [How does Function Calling work in LLMs?](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fhow-does-function-calling-work-in-llms)\n\n---\n\n## AI Agent Loop\n\nIn this blog, we will learn about the AI Agent Loop - what it is, why an AI Agent needs it, the think-act-observe cycle that powers it, how the loop knows when to stop, and the common ways the loop fails.\n\nWe will cover the following:\n\n- The Big Picture\n- What is the AI Agent Loop\n- Why an AI Agent Needs a Loop\n- The Think-Act-Observe Cycle\n- The Loop Step by Step\n- The Loop in Real Code\n- Parallel Tool Calls in One Turn\n- How the Loop Knows When to Stop\n- Common Loop Failures\n- Quick Summary\n\nLet's get started: [AI Agent Loop](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-agent-loop)\n\n---\n\n## ReAct Agent\n\nIn this blog, we will learn about the ReAct Agent - what it is, how it is built, its anatomy, how it thinks and acts, and how to handle its common failure modes.\n\nWhen we hear **ReAct Agent**, it sounds complex. But do not worry. If we break it down into its individual parts, every single piece is simple.\n\nWe will cover the following:\n\n- What is a ReAct Agent\n- ReAct Agent vs AI Agent\n- Anatomy of a ReAct Agent\n- The ReAct Prompt Template\n- How a ReAct Agent Thinks and Acts\n- A Full Trace Example\n- Implementing a ReAct Agent\n- Common Failure Modes and How to Fix Them\n- Quick Summary\n\nLet's get started: [ReAct Agent](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Freact-agent)\n\n---\n\n## Reflection Agent\n\nIn this blog, we will learn about the Reflection Agent - what it is, how it is built, its anatomy, how it generates, critiques, and revises its own work, and how to handle its common failure modes.\n\nWe will cover the following:\n\n- What is a Reflection Agent\n- Reflection Agent vs AI Agent\n- Anatomy of a Reflection Agent\n- How a Reflection Agent Works\n- A Full Trace Example\n- Reflection Agent vs ReAct Agent\n- Common Failure Modes and How to Fix Them\n- Quick Summary\n\nLet's get started: [Reflection Agent](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Freflection-agent)\n\n---\n\n## Plan-and-Execute Agent\n\nIn this blog, we will learn about the Plan-and-Execute Agent - what it is, its anatomy, how it plans and runs the steps, how it differs from a ReAct Agent, and how to handle its common failure modes.\n\nWe will cover the following:\n\n- What is a Plan-and-Execute Agent\n- Plan-and-Execute Agent vs AI Agent\n- Anatomy of a Plan-and-Execute Agent\n- How a Plan-and-Execute Agent Works\n- A Full Trace Example\n- Plan-and-Execute Agent vs ReAct Agent\n- Common Failure Modes and How to Fix Them\n- Quick Summary\n\nLet's get started: [Plan-and-Execute Agent](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fplan-and-execute-agent)\n\n---\n\n## AI Agent Memory\n\nIn this blog, we will learn about AI Agent Memory - why agents need it, the memory stack, the four core operations (write, read, update, forget), how memory flows at runtime, and the common mistakes.\n\nWe will cover the following:\n\n- The Big Picture\n- Why AI Agents Need Memory\n- The Memory Stack\n- The Four Core Operations\n- How Memory Flows at Runtime\n- What to Store and What Not to Store\n- Common Mistakes and How to Fix Them\n- Quick Summary\n\nLet's get started: [AI Agent Memory](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-agent-memory)\n\n---\n\n## Context Engineering\n\nIn this blog, we will learn about Context Engineering - what it is, why it has become the most important skill for building reliable AI applications, how it differs from Prompt Engineering, the components that make up the context, common patterns like RAG, few-shot examples, tools, and memory, and the best practices and common mistakes to keep in mind.\n\nWe will cover the following:\n\n- What is Context Engineering?\n- The Big Picture\n- Why Context Engineering matters\n- Prompt Engineering vs Context Engineering\n- The components of the context\n- Common patterns in Context Engineering\n- Common mistakes to avoid\n- Best practices\n- Quick Summary\n\nLet's get started: [Context Engineering](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fcontext-engineering)\n\n---\n\n## Agentic RAG\n\nIn this blog, we will learn about Agentic RAG - what it is, why standard RAG falls short, the agentic RAG loop, the three building blocks, the common patterns, when to use it, and the limitations to keep in mind.\n\nA hard question often needs more than one search. Some of those searches need different sources. Some depend on what the previous search found. Standard RAG cannot do any of this. Agentic RAG can.\n\n**Agentic RAG = Agentic + RAG**\n\nWe will cover the following in this blog:\n\n- The Big Picture\n- A Quick Recap of RAG\n- A Quick Recap of AI Agent\n- Why Standard RAG Falls Short\n- What is Agentic RAG\n- The Agentic RAG Loop\n- The Three Building Blocks\n- A Walkthrough with a Real Example\n- Common Patterns of Agentic RAG\n- Standard RAG vs Agentic RAG\n- When to Use Agentic RAG\n- Limitations of Agentic RAG\n- Quick Summary\n\nLet's get started: [Agentic RAG](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fagentic-rag)\n\n---\n\n## GraphRAG\n\nIn this blog, we will learn about GraphRAG and how it improves retrieval by using a knowledge graph along with [vector search](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fhow-does-a-vector-database-work).\n\nWe will cover the following:\n\n- What is GraphRAG?\n- Why normal RAG is not enough\n- The big picture of GraphRAG\n- How GraphRAG builds the knowledge graph\n- How GraphRAG answers a question\n- Local search vs Global search\n- When to use GraphRAG\n- Trade-offs of GraphRAG\n- Quick Summary\n\nLet's get started: [GraphRAG](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fgraphrag)\n\n---\n\n## Multi-Agent Systems\n\nIn this blog, we will learn about Multi-Agent Systems - what they are, the three pillars that hold them together, the common agent roles, how agents communicate and coordinate, the trade-offs, and when to use them.\n\nWe will cover the following:\n\n- The Big Picture\n- What is a Multi-Agent System\n- The Three Pillars\n- Common Agent Roles\n- How Agents Communicate\n- How Agents Coordinate\n- Multi-Agent vs Single Agent - The Trade-offs\n- Common Mistakes\n- When to Use a Multi-Agent System\n- Quick Summary\n\nLet's get started: [Multi-Agent Systems](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fmulti-agent-systems)\n\n---\n\n## AI SubAgents\n\nIn this blog, we will learn about AI SubAgents. We will understand what they are, why we need them, how they work, and how to use them to build AI systems that can handle big and complex tasks.\n\nWe will cover the following:\n\n- What is an AI Agent?\n- What are AI SubAgents?\n- Why do we need SubAgents?\n- How do SubAgents work?\n- Example use case\n- Benefits of using SubAgents\n- Challenges with SubAgents\n- Best practices\n\nLet's get started: [AI SubAgents](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-subagents)\n\n---\n\n## AI Orchestration\n\nIn this blog, we will learn about AI Orchestration. We will understand what it is, why we need it, how it is different from AI Agents, and the common patterns we use to coordinate multiple LLMs, tools, and steps together to build real AI products.\n\nWe will cover the following:\n\n- What is AI Orchestration?\n- Why do we need AI Orchestration?\n- AI Orchestration vs AI Agents\n- Components of AI Orchestration\n- How AI Orchestration works\n- Patterns of AI Orchestration\n- Sequential Pattern\n- Parallel Pattern\n- Conditional Pattern\n- Loop Pattern\n- Orchestrator-Worker Pattern\n- Tools for AI Orchestration\n- Challenges in AI Orchestration\n- Best Practices\n\nLet's get started: [AI Orchestration](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-orchestration)\n\n---\n\n## How AI Agents Communicate\n\nIn this blog, we will learn about how AI agents communicate. We will understand why agents need to communicate, the main ways they talk to each other, the message format, and the protocols that make agents work together to finish complex tasks.\n\nWe will cover the following:\n\n- What is agent communication?\n- Why do agents need to communicate?\n- What agents need in order to communicate\n- How a message flows between agents\n- The ways AI agents communicate\n- Direct Communication\n- Centralized Communication\n- Broadcast Communication\n- Shared Memory Communication\n- What a message looks like\n- The rules agents follow to talk\n- Challenges when agents communicate\n- Best Practices\n\nLet's get started: [How AI Agents Communicate](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fhow-ai-agents-communicate)\n\n---\n\n## How do Computer-Use Agents work?\n\nIn this blog, we will learn about how computer-use agents work.\n\nWe will cover the following:\n\n- What is a computer-use agent?\n- Why do we need a computer-use agent?\n- The perceive, think, act loop\n- How does the agent see the screen?\n- How does the agent decide what to do?\n- How does the agent take actions?\n- A step-by-step walkthrough with an example\n- The system prompt and tools\n- Safety and guardrails\n- Limitations of computer-use agents\n- Conclusion\n\nLet's get started: [How do Computer-Use Agents work?](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fhow-do-computer-use-agents-work)\n\n---\n\n## How does LangChain work?\n\nIn this blog, we will learn about how LangChain works. We will also see why we need it, what chains, prompts, memory, and output parsers are, how retrieval and agents fit in, and how the full flow works together in the real world.\n\nWe will cover the following:\n\n- What is LangChain?\n- Why do we need LangChain?\n- The core idea behind LangChain\n- LLM and Prompt Template\n- What is a Chain?\n- Output Parser\n- Memory\n- Retrieval and RAG\n- Tools and Agents\n- A complete flow of how LangChain works\n\nLet's get started: [How does LangChain work?](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fhow-does-langchain-work)\n\n---\n\n## How does LangGraph work?\n\nIn this blog, we will learn about how LangGraph works. We will also see why we need it, what graphs, state, nodes, and edges are, how tools work and who actually calls them, how memory and human-in-the-loop fit in through a complete example, and when to use it in the real world.\n\nWe will cover the following:\n\n- What is LangGraph?\n- Why do we need LangGraph?\n- What is a Graph in LangGraph?\n- What is State in LangGraph?\n- Nodes and Edges\n- Conditional Edges\n- A complete example\n- Tools and who calls them\n- Memory and persistence\n- Human-in-the-loop\n- When to use LangGraph\n\nLet's get started: [How does LangGraph work?](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fhow-does-langgraph-work)\n\n---\n\n## Harness Engineering in AI\n\nIn this blog, we will learn about Harness Engineering in AI. We will understand what a harness is, why we need it, and how it is used in AI Agents and evaluation systems.\n\nWe will cover the following:\n\n- What is a Harness in AI?\n- Why do we need Harness Engineering?\n- Components of an AI Harness\n- Harness Engineering for AI Agents\n- Harness Engineering for Evaluation\n- Best Practices in Harness Engineering\n- Putting It All Together\n\nLet's get started: [Harness Engineering in AI](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fharness-engineering-in-ai)\n\n---\n\n## AI Agent Observability\n\nIn this blog, we will learn about AI Agent Observability. We will also see why we need it, how it is different from normal software monitoring, what we must observe inside an agent, the key concepts like traces and spans, the metrics we must track, the tools we can use, and the best practices to follow.\n\nWe will cover the following:\n\n- What is an AI Agent?\n- What is Observability?\n- What is AI Agent Observability?\n- Why do we need AI Agent Observability?\n- How is AI Agent Observability different from traditional Observability?\n- The Three Pillars of Observability\n- Traces and Spans\n- What should we observe inside an AI Agent?\n- Key Metrics for AI Agent Observability\n- How AI Agent Observability works\n- Tools and Frameworks for AI Agent Observability\n- Observability vs Evaluation\n- Challenges in AI Agent Observability\n- Best Practices\n\nLet's get started: [AI Agent Observability](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-agent-observability)\n\n---\n\n## AI Agent Evaluation\n\nIn this blog, we will learn about AI Agent Evaluation. We will also see why it is different from LLM Evaluation, the types of evaluation we can do, the key metrics we must track, the methods we can use, and the best practices to follow.\n\nWe will cover the following:\n\n- What is an AI Agent?\n- What is AI Agent Evaluation?\n- Why do we need AI Agent Evaluation?\n- How is AI Agent Evaluation different from LLM Evaluation?\n- Types of AI Agent Evaluation\n- Outcome Evaluation\n- Trajectory Evaluation\n- Tool Use Evaluation\n- Planning Evaluation\n- Key Metrics for AI Agents\n- Agent Benchmarks\n- Methods to Evaluate AI Agents\n- Frameworks and Tools for AI Agent Evaluation\n- Challenges in AI Agent Evaluation\n- Best Practices\n\nLet's get started: [AI Agent Evaluation](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fai-agent-evaluation)\n\n---\n\n## Decoding Sakana Fugu Technical Report\n\nIn this blog, we are going to learn about Sakana Fugu, a family of AI models that work like a conductor for a team of other AI models.\n\nWe will cover the following:\n\n- What is Sakana Fugu?\n- Why Fugu was needed\n- The big picture: what Fugu does\n- Collective Intelligence\n- The two Fugus - Fugu and Fugu-Ultra\n- How Fugu picks the right model - the lightweight selection head\n- Teaching Fugu who is best - supervised fine-tuning\n- Polishing Fugu on real tasks - evolutionary strategies\n- How Fugu-Ultra conducts an orchestra - the Conductor\n- Teaching Fugu-Ultra to conduct - GRPO\n- Stopping the agents from copying each other\n- How well does Fugu perform?\n- The clever strategies Fugu discovered on its own\n- Quick Summary\n\nLet's get started: [Decoding Sakana Fugu Technical Report](https:\u002F\u002Foutcomeschool.com\u002Fblog\u002Fdecoding-sakana-fugu)\n\n---\n\n## More blogs and videos coming soon!\n\n### License\n```\n   Copyright (C) 2026 Outcome School\n\n   Licensed under the Apache License, Version 2.0 (the \"License\");\n   you may not use this file except in compliance with the License.\n   You may obtain a copy of the License at\n\n       http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\n   Unless required by applicable law or agreed to in writing, software\n   distributed under the License is distributed on an \"AS IS\" BASIS,\n   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n   See the License for the specific language governing permissions and\n   limitations under the License.\n```\n","这是一个面向初学者的AI智能体开发教程项目，系统讲解从基础到进阶的AI Agent构建方法。涵盖函数调用（Function Calling）、智能体循环（Agent Loop）、多智能体系统（Multi-agent Systems）、智能体编排（Orchestration）与评估（Evaluation）等核心模块，并结合LLM、RAG、MCP等底层技术背景展开。内容以概念解析、工作原理拆解和代码级示例为主，强调工程实践与常见失败模式分析。适用于AI工程师、LLM应用开发者及希望系统掌握智能体架构设计的技术学习者。","2026-07-08 04:29:57","CREATED_QUERY"]