인프런 - 라이프타임 커리어 플랫폼

Beyond the era of simply using AI, we are now in an era that requires people who can design AI. This course is a master roadmap that systematically organizes the entire design map of AI agents, from "Introduction → Structure → Design → Operation." Based on RAG, Tool Calling, Memory, and Multi-Agent structures, you will learn how to design and scale AI agents from an architect's perspective. If you want to grow into someone who designs AI systems rather than just someone who "uses" AI, this course will provide the direction.

It's okay if you don't know a single line of code. We are now in the era of 'Vibe Coding,' where you develop by 'conversing' with AI.

Build your own AI headquarters at a low cost! This is a practical guide to building autonomous AI agents that combine Gemini 2.5 Flash and Docker to ensure security while reducing costs.

This is a course to learn the concepts and usage methods of the LangChain library, and to build your own ChatGPT using the LangChain library.

What if ChatGPT were embedded within your own application? In this lecture, we will develop various programs using the ChatGPT API. We will cover all processes in detail, from basic API usage to program creation and deployment.

Create a program using the GPT API, and even generate images and videos!

This course is a hands-on program for implementing generative AI applications based on text, images, voice, and documents using the OpenAI API. Starting from setting up the Anaconda and Jupyter Notebook environment, it covers essential development environment configurations for practical work, including API Key management and understanding costs and tokens. Based on the latest Responses API, you'll implement text generation, summarization, classification, Vision (image understanding), voice processing, and PDF input processing, while practicing core features used directly in the field step-by-step, such as Function Calling, Structured Outputs (Pydantic), Embedding, and RAG (File Search). Additionally, including Web Search, Code Interpreter, Streaming, Background tasks, and Conversation State management, you'll learn how to expand beyond simple API calls to 'intelligent AI services'. Finally, the goal is to implement agent-based AI systems that autonomously select and execute tools using the Agents SDK and MCP (Model Context Protocol), while learning the structure and design perspectives necessary for actual service development.

[Understanding AI Foundation Models and Their Operating Principles: Engineering Control and System Architecture, Practical Methodologies for Resolving AI Uncertainty and Engineering Assetization] 1. Introduction: The Necessity of Engineering Control of Intelligence (Engineering Control vs. Systemic Chaos) A core conclusion derived from long-term practical insights in industrial fields is that power that is not properly controlled acts as a potential liability rather than an asset. Even a high-performance engine is nothing more than an unstable physical mass if it lacks sophisticated combustion logic and microsecond-level control systems. The organizational chaos currently appearing in the process of adopting Generative AI is judged to stem from a lack of understanding of these control principles and a blind faith in technical "black boxes." This masterclass redefines Artificial Intelligence not as a mysterious stochastic phenomenon, but from the perspective of Model-Based Engineering (MBE). By transforming the uncertain domain of intelligence into a predictable and reliable engineering framework, we aim to present a strategic methodology that allows organizations to secure strong leadership across the entire system without being dependent on technical trends. 2. The 4 Pillars for Solving Core Challenges ① Epistemological Paradigm Shift: Visualizing the Black Box and Assetizing Technical Debt Many companies are facing "technical debt"—characterized by exposure to security vulnerabilities and exponential increases in maintenance costs—by adopting AI models without a clear understanding of their internal structures. This course assetizes this through the following approaches: Deconstruction of Mechanisms: We engineeringly deconstruct the Self-Attention mechanism, the core of the Transformer architecture, from the perspective of numerical weight analysis. By understanding the numerical mechanisms that determine information priority, we visualize the basis for the model's judgment. Analysis of ID Formation: We transparently track the process by which a series of pipelines—leading from Pre-training to Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF)—forms the model's technical identity and ethical guidelines. This converts invisible threats into controllable system parameters. ② Securing Deterministic Reliability: Hallucination Control Strategies to Overcome Probabilistic Limits Large Language Models (LLMs) are not systems that reason for truth, but systems that generate the next most probable token. The "hallucination" phenomenon resulting from this inherent characteristic becomes a fatal flaw in engineering fields where reliability is vital. Constraints of Retrieval-Augmented Generation (RAG): We move away from closed structures that rely solely on the model's internal fixed memory (Internal Weights). We establish an "open-book strategy" that provides clear grounding for generated results by allowing real-time reference to trusted external knowledge bases. Hybrid Model Architecture: We design a redundancy strategy that achieves both accuracy and operational efficiency by deploying large models for areas requiring enterprise-wide knowledge and optimized Small Language Models (SLMs) for specific domains where security and real-time response are essential. ③ Computing Architecture Optimization: Overcoming Physical Bottlenecks (Memory Wall) While intelligence is implemented in software, its performance and economic sustainability are defined by the physical limits of hardware. Physical Constraint Analysis: We diagnose the "Memory Wall" problem, where data transfer speeds cannot keep up with the processing speeds of computing units, and heat generation issues resulting from high-density computation from an engineering perspective. Infrastructure Design Capability: We precisely analyze the physical impact of High Bandwidth Memory (HBM) stacking structures and 2.5D/3D advanced packaging technologies on inference efficiency. We cultivate design capabilities to optimize Total Cost of Ownership (TCO) through full-stack integrated insights that complement hardware limitations with software architecture. ④ Acceleration of Functional Expansion: Transitioning from Passive Tools to Autonomous Agent Systems Current AI remains at the level of simple Q&A, failing to create added value for practical business automation. This course evolves AI into an active subject that judges and executes on its own. Decomposition: We learn techniques for decomposing complex goals into achievable sub-tasks and logically organizing the execution sequence upon receiving them. Digital Workforce Deployment: We define the process of applying "Active Agent" systems to the field, which autonomously call internal ERPs, browsers, and external APIs to complete actual business logic and accept feedback on results. 3. Core Architecture: Closed-loop Control System The way an AI agent manifests intelligence and performs complex tasks is theoretically identical in logical structure to the closed-loop control system performed by an ECU (Electronic Control Unit), the core brain of a car. This course analyzes this in detail from the perspective of the ReAct (Reasoning and Acting) framework. First, the system begins at the Input stage, receiving ambiguous and complex requests from the user. This plays the same role as a sensor in control engineering collecting physical data from the external environment and delivering it to the system, serving as the standard for defining the initial state of the task at hand. Second, based on the received data, the Thought stage proceeds, where plans are established through logical reasoning within the LLM architecture. This is in line with the process where control algorithms in an ECU calculate optimal control values by processing input sensor data. At this stage, the agent sets the optimal path to achieve the goal and secures the logical rigor of the system. Third, the Action stage follows, where tasks are completed by calling external tools or APIs according to the established plan. This logically matches the mechanism where the calculation results of a control system are converted into physical power through an actuator to execute commands. Through this, intelligence exerts actual physical and digital influence beyond abstraction. Finally, the Observation stage is performed, analyzing the execution results and correcting errors relative to the initial goal. This is identical to the core principle of control engineering, which reduces system deviation through a feedback loop. The agent self-verifies whether the execution results meet the goal and continuously upgrades performance by reflecting occurred errors into the next action plan. AI equipped with such a closed-loop structure is no longer an incomplete system dependent on probability. By securing engineering rigor that self-verifies execution results and corrects errors, it functions as a trust-based partner capable of performing business-critical tasks. 4. Practical Application and Expansion: Software-Defined Vehicles (SDV) and Physical AI The final destination of AI architecture lies in the cross-industry proliferation of Software-Defined Vehicles (SDV) and Physical AI, which overcome and evolve physical constraints through software intelligence. This is the standard model for future System Integration (SI) across manufacturing and service industries. Securing Edge Intelligence and Data Sovereignty: Small models (SLMs) mounted on-device in vehicles or facilities learn real-time field data immediately. This minimizes cloud dependency, perfectly protecting data sovereignty—a core asset of the company—and enables precision services based on ultra-low latency. Hardware Optimization and Lightweight Engineering: To implement the best intelligence within limited power and computational resources, we actively introduce model compression technologies such as Quantization, Pruning, and Knowledge Distillation. Model deployment considering hardware bandwidth becomes a core competency that determines system response speed and user experience. Hybrid Orchestration: We design an integrated architecture that organically connects "Cloud LLMs" possessing broad general knowledge with "Edge SLMs" specialized for specific physical control and security. Integration from a full-stack perspective, penetrating from silicon chipsets to software stacks, provides a powerful competitive advantage that evolves the entire system through software updates alone. 5. Conclusion: The Role and Vision of the AI Architect The ultimate goal of this masterclass is to elevate students from the position of a "User" who passively relies on technology and hopes for luck, to a professional "AI Architect" who perfectly controls and tunes everything from the physical limits of the system to the depths of the software architecture. While the phenomenon of intelligence manifests from software logic, it is silicon (hardware) that defines the physical limits of that intelligence, and only sophisticated engineering can overcome those limits to complete actual business value. "Intelligence may reside in the realm of probability, but the vessel that contains that intelligence and makes it operate according to purpose must belong solely to the realm of rigorous and sophisticated engineering."

We are revealing the entire process—without filters—of how non-developers built a Slack bot from scratch, including all the trial and error along the way.

This course is an advanced program focused on designing Multi-LLM architectures and orchestration-centered Agent systems by strategically combining GPT, Gemini, and LLaMA based on Spring AI. Moving beyond simple LLM calls, you will implement scalable, stable, and continuously improving AI systems by applying Workflow Patterns and Multi-Agent structures. Furthermore, the course covers Circuit Breakers, Reactive Streams, Redis monitoring, parallel processing, and iterative evaluation loops to complete your capability in designing production-grade AI architectures. The ultimate goal is to grow into a developer who can design AI systems, rather than just being an AI user. 🚀

As "Vibe Coding" becomes a trend, courses are flooding the market. But if you look closely, they are all the same. "How to use Cursor," "Mastering Copilot," "Building apps with this tool." Tools change. Tools that were the standard six months ago are now used by no one. Copilot was the trend, then Cursor arrived, and now that Cursor is the trend, Claude Code has arrived. If you only learn how to use a specific tool, everything you've learned becomes zero the moment that tool changes. This course teaches a workflow that applies even when tools change. It can be applied to any language, any framework, and any project.

How long are you going to manually look through 2,500 stocks every day? Searching through Naver Finance to find surging stocks after the market closes, Reading news to judge whether it's good or bad news, Checking foreign/institutional supply and demand one by one, Opening charts to analyze patterns... Aren't you repeating this every single day? I used to do that too. I spent 2 to 3 hours after work analyzing stocks, and yet I still missed more stocks than I found. With over 2,500 stocks across KOSPI and KOSDAQ combined, it's impossible for a human to see them all every day. --- So, I built a system. I created a system that automatically analyzes 2,500 stocks every day after the market closes. - Automatically collects market prices, supply/demand, and news - AI (Gemini) reads the news and determines if it's positive or negative - Scores stocks out of 15 points based on 6 factors - Selects only the stocks that pass the criteria and calculates entry, stop-loss, and take-profit prices - Sends notifications via Telegram Now, I just check my phone after work. Additionally, every Saturday, the system analyzes its own performance from the past week and automatically adjusts stop-loss lines, take-profit lines, and holding periods. It is a structure where the system learns and improves on its own. --- But I am not a developer. I didn't write the code for this system myself. I gave all the instructions to the AI verbally. "Filter out stocks that rose more than 5% today with a trading volume exceeding 50 billion won." "Send these 3 news articles to Gemini and have it judge if they are positive." "Create a scheduler so this runs automatically every day at 4 PM." When I speak like this, the AI (Claude) generates the code. This is "Vibe Coding." --- In this course, we will build this exact system. Over 58 lessons, we will build the system I actually use every day from start to finish. Starting from data collection, AI news analysis, scoring engine, signal generation, Flask API server, Next.js web dashboard, Telegram automatic notifications, and even the self-learning system. The final product is not a Jupyter Notebook. The final product is a web dashboard and Telegram notifications that actually run every day. You don't need to know how to code. In every lesson, I will show you how to talk to Claude, and if you follow along, you will get the same results. --- Recommended for: - Office worker investors who lack the time to analyze stocks every day - Those who want an automated system but don't know how to code - Those curious about quant/system trading but don't know where to start - Those curious about how to utilize AI in practice --- ⚠️ This course does not guarantee investment returns. This is a programming course on building your own stock analysis tools. Actual investment decisions are the responsibility of the student.

From PC control to high-level research and app development A guide to building your own 'AI Work Assistant' ready for immediate real-world deployment

We are now in an era where anyone can create services without coding. The Selfish Club crew members implemented services for actual use in just three weeks by selecting only the essential features. These are examples of crew members who don't know how to code, solving problems themselves by building services using only natural language prompts. Vibe coding is no longer a foreign concept! We are sharing all the real-world examples of "what problems can actually be solved through coding!"

No coding skills? No problem! Turn your ideas into real profit in just 4 weeks. Use AI and the latest tools to build a website and an app simultaneously and launch your service right away.

AI Work Automation + Side Income Generation with Just One Click!!! Make, the ultimate work automation tool - have you been hesitating to start due to its complex settings and features? Build the automation you've been dreaming of with step-by-step lectures that even beginners can easily follow.

Master prompt engineering perfectly, an essential skill for developers in the AI era.

This lecture is for those who have learned Python but are unsure of how to use it. Utilize 99.9% of basic programming knowledge!!! Try making a Flutter voice translation app with basic example code by minimizing difficult code. Talk to chatGPT, translate conversations with foreign friends, draw images with voice, and upgrade the conversation app with fine tuning.

This is a lecture directly from the author of <Prompt Engineering>. Learn to use ChatGPT, Bing, Bard, HyperCLOVA X, and more with ease.

Hello, I'm Woney. I specialize in one thing only: developing TradingView indicators. I believe that what's more important than "looking pretty" is having clear rules that don't waver in real trading, stable operation, and handling exceptional situations. [Indicators I Create] - Condition-based signals/alerts (alarms) - Entry/exit assistance, trend/volatility/volume-based filters - Guards to prevent over-entry/risk management (can be made optional) - Chart readability improvements (labels/lines/status windows/tables, etc.) [Development Process] 1) You provide your desired conditions "in words" → I structure them into indicator rules. 2) To avoid confusion on the chart → I organize the display methods (labels/lines/tables) together. 3) I proactively check for potential issues in real trading (duplicate signals, exceptional periods, etc.) and implement them stably. [Recommended For] - Those who have desired conditions but find implementation difficult - Those who need filters/refinement because they have too many or too few signals - Those who need readable indicators that users can understand immediately