Every idea, drawn and set in motion.
Each lesson is a diagram you step through. Watch requests flow, caches fill, agents loop and things break — then see the fix land. Go in order or jump to what you need.
AI Foundations
Machine learning, deep learning, NLP, computer vision, reinforcement learning and the techniques underneath modern AI.
How LLMs Work
Tokens, attention, transformers, embeddings and the inference pipeline — from text in to text out.
Choosing Models
The model landscape, capability assessment, pricing, and how to pick the right model for the job.
Training & Adaptation
Pretraining, fine-tuning, LoRA, RLHF/DPO, distillation, synthetic data, quantization and reasoning models.
Inference & Serving
KV cache, batching, speculative decoding, paged attention, serving stacks and the cost playbook.
Prompting & Context
Prompt fundamentals, few-shot, chain/tree of thought, context engineering, structured output and injection defense.
Retrieval & RAG
Chunking, embeddings, vector databases, hybrid search, reranking, GraphRAG, agentic RAG and RAG at scale.
Agentic Systems
Agent loops, ReAct, tool use and MCP, multi-agent orchestration, planning, recovery, HITL and durable execution.
Memory & State
Short- and long-term memory, agentic memory, semantic caching and state management.
Frameworks & Tools
LangChain, LangGraph, LlamaIndex, DSPy, multi-agent frameworks, coding agents — and how to choose.
Document Processing
OCR, layout analysis and turning messy documents into clean, retrievable structure.
Generative AI
Text, image, video, audio and code generation — the model families, design patterns and how they are built.
Conversational AI
Dialogue systems from classical NLU pipelines to LLM assistants and voice — memory, design patterns and evaluation.
Backend for AI
REST, HTTP, async, streaming, auth, databases, caching, queues, jobs, rate limits, idempotency, retries and observability.
Deployment & Delivery
Docker, Kubernetes, CI/CD, eval gates, IaC, GPUs, autoscaling, canaries, flags, versioning, health checks and rollbacks.
LLM Infrastructure & FinOps
LLM infrastructure, CI/CD for AI, gateways and model routing, FinOps and token economics.
MLOps
The ML lifecycle in production: versioning, registries, CI/CD, infrastructure, automation, monitoring and drift.
AIOps
AI for IT operations: data sources, anomaly detection, correlation, root-cause analysis, tools and use cases.
AI Security
Prompt injection, jailbreaks, OWASP LLM Top 10, guardrails, PII, least privilege, sandboxing, secrets, approvals, audit and red teaming.
Reliability & Safety
Guardrails, ensembles, reliability patterns, governance and compliance.
Evaluation & Observability
LLM evaluation, LLM-as-judge, tracing and observability, and reading benchmarks honestly.
Design Patterns
Reusable AI system patterns — and the anti-patterns that sink projects.
Tool Use & Computer Agents
Tool-use architectures, computer-use agents, building tool agents safely.
Voice & Multimodal
Real-time voice agents and multimodal generation.
Case Studies
Whole systems, end to end: enterprise RAG, coding agents, support automation, fraud, voice AI and more.
Lessons are adapted from the open-source AI System Design Guide (MIT) — the full chapters live in the guide library.