LLM Application In Production

We explore how to create an AI judge by combining knowledge graphs, reasoning systems, and various agent frameworks such as CrewAI, LangChain, and AutoGen, which enable the implementation of LLM-based multi-agent technology.

LLM: A pro quickly delivers core content, from essentials to practical tips!

An introductory course that covers the core of LLMs, Agents, and RAG using LangChain v1.0+'s simplified API and free LLMs (Gemini · Groq · Ollama), all without the burden of credit card registration.

This is the edited live video from the LLM Application Experience Sharing Session with knowledge sharer Kang Byung-jin :)

Develop various features using Spring WebFlux. This course will teach you WebFlux's essential concepts and practical implementation.

We examine AI security incidents and the role of red teams, then set up an LLM practice environment in our own AWS account. From capturing the initial response to checking usage and cleaning up resources, we record everything in the Mission 0 checklist. The prompt injection diagnosis exercise continues in Part 4.

This is a practical course on building a RAG-based document search system using the OpenAI API and Spring AI in a Spring Boot environment. You will learn the entire process of developing an AI assistant step by step, from the concepts of Prompt Engineering, Vector Stores, and Embeddings to rapid prototyping with Dify, MCP tool integration, multimodality, and guardrails. You can learn practical application strategies by comparing direct implementation with the use of no-code tools. 🆕 [Update] Section 4 now includes a supplementary lecture (1 hour) on TypeSafe’s Jev decision-making model, covering how to design an agent’s decision-making logic in greater depth.

This is a hands-on tutorial on how to integrate with IntelliJ and develop quickly using the Model Context Protocol (MCP).

Based on the LLM Wiki architecture proposed by Andrej Karpathy, we are freely releasing a practical pipeline and MIT open-source starter kit that automatically compiles five scattered Markdown notes (8,615 characters) into nine wiki documents (23,659 characters) and a knowledge graph with 44 bidirectional [[wikilinks]] in just 1 minute and 42 seconds.

From tokens and context to RAG, agents, and guardrails, we examine how AI services work from a security perspective. We compare the concepts with the provided backend code and organize the areas to inspect across input, retrieval, and tool calls into a single attack-surface map.

Before execution, define the scope, rules of engagement, test conditions, and grounds for assessment. Link AI assets and trust boundaries with STRIDE scenarios to create a red team plan and threat model, and distinguish what can be stated based on the results of repeated tests.

Solve the point where 80% get stuck at makeathons. Complete Raspberry Pi · Computer Vision · LLM · 3D Design in 4 weeks! Achieve top rankings at makeathons with a demonstrable smart mirror PoC!

Explore how LLM applications are shifting the development paradigm. Understand why LLMs are becoming a sustainable core technology through comparisons with existing technologies, and learn about the essential skills and mindset shifts required for developers. Gain insights from expert instructors to grasp the essence and future direction of LLM application development.

As an ambassador for the Cloud Native Computing Foundation (CNCF), I have given talks at KubeCon on topics such as Kubernetes security and policy, the scheduler, and Gateway API. I also serve as an ambassador for the Agentic AI Foundation (AAIF), where I present findings from hands-on research and measurements of AI agents, LLMs, MCP, and AGENTS.md in Kubernetes environments. This course includes Korean-language recordings of talks I have given in English at international events such as KubeCon, Open Source Summit, MCP Dev Summit, and AGNTCon + MCPCon, and I add each recording as it becomes available.

Learn the entire process of running the latest Gemma 4 model directly on your MacBook without the burden of paid API costs. You will master performance maximization techniques using Apple Silicon's Metal API and optimal parameter settings for different VRAM capacities, while gaining the ability to build production-level local AI infrastructure based on FastAPI.

"How is a 1-trillion parameter model trained?" Discover the scaling strategy of Kimi K2.5, revealed directly on stage by Moonshot AI at GTC 2026, in Korean on Inflearn. 2x token efficiency · 1 million token context · 1,000 agent swarm The next step for open-source LLMs is here. * This lecture is released for free through an official collaboration between Moonshot AI, the creator of Kimi, and Inflearn.

We built a harness (rule files, blocking hooks, and completion gates) from 8 real-world incidents to prevent accidents where AI agents report “done” without verification, delete entire folders, or overwrite one another’s work across sessions—and we’re releasing it as a free starter kit. Alongside measured results from running the same instructions 16 times with and without the harness, we’ll show you in 10 minutes how to make AI’s “done” speak in verification numbers.

Before installing the caveman skill that has earned over 110,000 stars with its “65% token reduction” claim, I tested it myself. I ran the same questions 156 times in Claude Code under four conditions—default, “Answer concisely,” caveman, and ultracave—and used a script to count output tokens and correct answers. In under 10 minutes, I’ll show you how to measure fairly and share a free measurement kit you can use with your own questions.

If you want to create your own AI service without coding, this course is the perfect solution. Using the Dify no-code platform, you can create high-quality AI apps with just your ideas. Instead of complex theory, it's structured around hands-on projects, allowing both AI beginners and working professionals to develop practical skills.

By utilizing the operating principles and development tools of Microsoft 365 Copilot agents, you can systematically learn how to design and expand agents that operate in the way you desire. Chapter 1 organizes the essential concepts and principles to know before creating an agent, Chapter 2 explores agent types and tools suitable for various scenarios, and Chapter 3 allows you to directly implement your own agent using Agent Builder, SharePoint Agent, and Copilot Studio. From basics to hands-on practice, this single course will enable you to connect the potential of Copilot agents to practical applications!