The Platform Engineer's Path #1intermediate

LLM Orchestration & RAG Systems

The skills every AI engineer needs: retrieval-augmented generation, vector databases, embedding pipelines, multi-step agents, and function calling. Build a production RAG app from scratch with evaluation and monitoring.

What You Build

A production RAG application with document ingestion, vector search, hybrid retrieval, evaluation suite, and deployed API

Sections

Lessons

Estimated

Concepts

Prerequisites

Zero to AI-Powered Developer

ragllmvector-databaseembeddingsagentslangchainorchestration

Alex (Primary)

conversational · energetic

First 5 lessons are free (38% of the course). No login required.

LLM Orchestration Foundations

Map the landscape: when to RAG, fine-tune, or prompt engineer. Architecture patterns for LLM applications.

The LLM Orchestration Landscape

25 min Build in Public

Tweet: Tweet: 'LangChain vs LlamaIndex vs custom — mapped the entire LLM orchestration landscape so you don't have to.'

When to RAG vs Fine-Tune vs Prompt Engineer

30 min Ship

Ship: Decision framework: flowchart for choosing RAG, fine-tuning, or prompt engineering for any use case

Architecture Patterns for LLM Apps

30 min Ship

Ship: Architecture diagram for 3 common LLM app patterns

Retrieval & Embeddings

Embedding models, vector databases, and chunking strategies that determine RAG quality.

Embedding Models: How Machines Understand Text

30 min Ship

Ship: Working embedding pipeline that converts documents to vectors

Vector Databases: Pinecone, Weaviate, Chroma

35 min Ship

Ship: Vector store loaded with 1000+ documents, queryable via API

Preview — content blurs halfway through

Chunking Strategies That Actually Matter

30 min

Unlock the rest of this course

$5 for full course or $25/mo for everything

See pricing

Build a RAG System

End-to-end RAG pipeline with hybrid search and evaluation.

Build a RAG Pipeline from Scratch

40 min

Hybrid Search: Combining Vector + Keyword

30 min

Evaluation: How to Know If Your RAG Is Working

35 min

Agents & Tool Use

Multi-step agents, function calling, structured output, and memory.

Multi-Step Agents: Planning & Tool Use

35 min

Function Calling & Structured Output

30 min

Memory Systems for Conversational AI

30 min

Final Ship

Build and deploy a production RAG application.

Ship a Production RAG App

50 min

Next Course

AI CI/CD, Observability & Cost Optimization

AI apps break differently than traditional software. Learn prompt version control, LLM evaluation pipelines, tracing with LangSmith and Langfuse, hallucination monitoring, and cost optimization through caching and model routing. Ship an AI ops dashboard.

LLM Orchestration & RAG Systems

What You Build

A production RAG application with document ingestion, vector search, hybrid retrieval, evaluation suite, and deployed API