AI & Agents Training
Everything you need to understand modern AI and agents.
A structured guide for engineers, architects, and AI leaders. From LLMs and RAG to agentic systems, MCP, and production deployment.
Claude Training
Curated enterprise training covering the full Claude ecosystem. 14 modules, 8 written guides, 4 phases. Prompt engineering, Claude Code, API integration, MCP, connectors, and security.
Prompting
System design & prompt engineering
Claude Code
CLI workflows & MCP servers
API & SDK
Streaming, tool use & batch
Enterprise
Security, connectors & governance
AI Evals Training
Learn how to evaluate AI systems rigorously. Build test datasets, run prompt evaluations, implement model-based and code-based grading, and create continuous eval pipelines for production AI applications.
Eval Design
Test datasets & grading rubrics
Model Grading
LLM-as-judge evaluation
Code Grading
Deterministic test assertions
CI Pipelines
Continuous eval in production
AI Training Unpacked
The podcast for engineers building with Claude.
Two engineers break down everything from how Claude processes text to building production MCP servers. No fluff, just the concepts and code you actually need. Listen while you commute, exercise, or code.
Why this matters. The AI landscape is moving fast. Structured knowledge is the advantage.
Models are evolving quarterly
GPT-5, Claude Opus 4.7, Gemini 2.5, Llama 4, DeepSeek-R1. New model families launch every few months, each with different strengths, pricing, and architectural innovations. Knowing what is available and when to use it is a competitive advantage.
The ecosystem is converging
MCP is becoming the universal standard for AI-tool integration, adopted by OpenAI, Google, and Microsoft. RAG, agentic patterns, and reasoning models are standard building blocks. Understanding these patterns means you can build on any platform.
Teams need structured knowledge
AI is no longer a research topic. Engineering teams are shipping AI products daily. This guide provides the structured foundation that turns scattered knowledge into confident decision-making.
Core Chapters
The foundation. Start here and work through in order.
Ch 1
FreeThe Foundation
How modern AI models work under the hood. Covers GPT, transformer architecture, how LLMs are trained, the full model landscape from OpenAI to open-weight alternatives, and the key concepts every practitioner needs.
Ch 2
FreeKnowledge & Retrieval
How AI systems store, find, and use information. Covers memory systems, RAG architecture (native and agentic), embedding models, vector databases, the fine-tuning vs RAG tradeoff, and data quality pipelines.
Ch 3
FreeAdvanced Intelligence
Reasoning, autonomy, and the techniques that make AI systems smarter. Covers reasoning models, agentic AI, prompt engineering, evaluation benchmarks, AI safety and alignment, and the future of the field.
Ch 4
StarterIntegration & Protocols
How AI systems connect and communicate through the Model Context Protocol. Covers MCP architecture, server and client implementation, Spring AI integration, and cloud platform stacks from AWS, Google, OpenAI, Anthropic, and Microsoft.
Ch 5
StarterBuilding AI Systems
Tools, SDKs, and putting it all together. Covers the full SDK landscape, how to choose the right stack, building a production assistant, and key takeaways from the entire guide.
Build and Ship
Capstone project, deployment, scaling, and production operations.
Ch 6
ProCapstone Project
Build a complete AI knowledge assistant from scratch. Combines RAG, MCP, and agent orchestration into one working application with full source code.
Ch 7
ProDeploy to Production
Containerize your AI agent with Docker, deploy to AWS/GCP/Azure, set up CI/CD pipelines, infrastructure as code, security hardening, and scaling strategies.
Ch 8
ProAdd a Web UI
Build a polished chat interface with Next.js and Vercel AI SDK. Streaming responses, tool call rendering, file uploads, and one-click deployment to Vercel.
Ch 9
ProScale with Async Processing
Handle thousands of concurrent users with task queues, batch processing, WebSocket streaming, semantic caching, and auto-scaling with Kubernetes.
Ch 10
ProMonitor in Production
Add observability with LangFuse tracing, continuous evaluation pipelines, alerting, A/B testing for prompts and models, and production hardening patterns.
Claude Code Cheatsheet
Single-page color-coded reference for all commands, shortcuts, flags, and environment variables.
Ready to go deeper?
Chapters 1-3 are free. Unlock the full 10-chapter guide, capstone project, production guides, and cheatsheets with a one-time purchase.