AI Engineering Learning Platform
For engineers who build AI and AI Agents and run them in production.
Pick a Learning Path, learn from the guides, and practice in the web IDE.
Choose Your Path
If AI is new to you, ease in with the entry course (AI Tutorial), build the shared base (AI Foundations), then choose the specialist path that matches your target role.
01 Entry — if AI is new to you
An entry course where you learn to use AI by solving requests like a game. Learn how to write a good request, how to verify an AI's answer, and how to handle material safely, all without code.
02 Shared foundations
The shared foundation you need for any AI specialization, from AI Agents to LLM Ops — built up in order from machine learning concepts to how Transformers and LLMs work to the practical libraries.
03 Choose an AI specialization
Targets the role of designing LLM-based AI Agents and RAG pipelines and shipping them as production services.
Lighter than autonomous Agents: targets the role of quickly building usable AI services by combining LLM APIs and RAG.
Targets the role of designing platform infrastructure so AI services can be deployed, scaled, and observed reliably.
Targets the role of taking an already-built AI application and reliably deploying, testing, and observing it under real traffic while keeping costs under control.
04 Production & Platform Engineering
Targets the role of designing and operating container-based workloads across multiple cloud environments.
Targets the role of building a reliable service operations practice with deployment automation and observability.
Targets the role of designing and implementing Spring-based microservice architectures.
Explore by Category
Every category starts with an Intro & Roadmap guide. Get the big picture first, then dive into the detailed guides.
Learn by Doing
Run what you learned from the guides right in the browser Lab, then build complete systems with hands-on AI Agent projects.
PRACTICE LAB
Separates the TypeScript-based cloud AI Agent from the private API server on the laptop. The cloud handles the user touchpoint, authentication, sessions, routing, and policy checks, while the laptop runs the Ollama LLM Engine, the FastAPI auth API, the Chroma Vector DB, and LangChain/LangGraph orchestration under Docker Compose.
FINReads the quantitative scores (SQLite) of the existing AutoTrading system, synthesizes stock reports with the Qwen 2.5 3B model, generates 768-dimension embeddings with nomic-embed-text, and loads them into pgvector (PostgreSQL). A LangChain ReAct agent then combines real-time Yahoo Finance tool calls with semantic RAG search to deliver detailed investment analysis.
OPSWhen an operations alert fires, summarizes the related logs and metrics and presents a safe recovery procedure and the points the owner needs to confirm.
EDUProvides a personal learning path and feedback based on the learner solution history, error patterns, and curriculum documents.
Books
The AIDevOps Cloud Native Series in reading-level order: start with the introduction, then move on to hands-on practice and production operations. The lab files for every book are free.

STEP 1 · Beginner
From Docker to Kubernetes: A Hands-On Guide to Containers with kind — 2026 Edition

STEP 2 · Core · hands-on
Hands-On Kubernetes with kind — From Core Concepts to Deployment and Operations — 2026 English Edition

STEP 3 · Advanced
Designing, Deploying, Scaling, Securing, Troubleshooting, and Operating Kubernetes in the Cloud
Featured
Field-tested practical guides from AIDevOps on system performance, AI service optimization, and more.
Covers the development, deployment, observability, performance, and quality-validation flow for turning an AI service into a product and running it.
Prompt management, RAG evaluation, Agent operations, LLM monitoring, cost optimization, and quality regression testing.
DB query optimization, Redis caching strategy, connection pool tuning, faster API responses, and k6 load testing.
Reducing LLM API latency, tuning inference servers, speeding up RAG pipelines, and k6 load testing.
Build a microservice architecture with API Gateway routing, auth filters, Config Server, and Eureka Service Discovery.
PROJECT INQUIRY
From AI Agent pipelines and Spring Cloud MSA APIs to cloud DevOps buildouts, we work on projects together, drawing on hands-on production experience.