local-ai·lab
local-ai-lab - a neural network flowing into ascending learning steps

Build local AI,
one lesson at a time.

A hands-on course where you build small, fully working programs from scratch - and understand every line. Everything runs on your own machine, with no API key required.

Start Lesson 1: RAG → Documentation View source on GitHub

The curriculum

Lesson 1

RAG from scratch

Extract → chunk → retrieve (BM25 + embeddings) → grounded answer with citations. A drag-and-drop document Q&A app.
✓ Available
Lesson 2

MCP servers

Expose your document search as a Model Context Protocol tool that Claude Code can call natively.
✓ Available
Lesson 3

Hybrid retrieval & reranking

Combine BM25 keyword search with a semantic arm and fuse them with Reciprocal Rank Fusion - offline, in Python, Node.js and C#.
✓ Available
Lesson 4

RAG safety & prompt injection

Treat retrieved documents as untrusted input - defend against prompt injection and poisoned content, in Python, Node.js and C#.
✓ Available
Lesson 5

RAG evaluation & regression testing

Golden questions, groundedness scoring, and regression tests - turn "seems good" into a tracked number, in Python, Node.js and C#.
✓ Available
Lesson 6

Repo-aware AI assistant

Ground an assistant in your codebase so it answers with cited, repo-specific context - and refuses when the answer isn't there - in Python, Node.js and C#.
✓ Available
Lesson 7

Rebuild RAG with LangChain

Rebuild the pipeline on LangChain, watch where it grounds differently, and price the swap - components replaced, lines you still write, packages you did not read.
✓ Available
Lesson 8

A stateful agent with LangGraph

Turn the pipeline into an agent that grades its own retrieval and searches again - then price the graph against the same loop written in sixty-three lines of plain while.
✓ Available
Lesson 9

Ollama + function calling

Let a local model pick its own tools, then put your code between its choice and anything that runs - schemas, caps, intent checks - and every local model scored on the same ten tasks.
✓ Available
Lesson 10 · special

Jev and System One models

A model that answers typed questions with a probability for every option. One real call to TypeSafe's Jev, then a simulated Jev on Ollama against rules and an LLM that writes JSON, on fake calls to an insurer's claims line and a newspaper's subscriber line.
✓ Available
Lesson 11

Microsoft Semantic Kernel

Rebuild the agent in C# / .NET with SK plugins and auto function calling - runs locally.
Planned
Lesson 12

AWS Bedrock Agents

Knowledge bases + action groups on a managed cloud agent, built and driven from your machine.
Planned
Lesson 13

Google AI Development Kit

Build and run a Gemini agent locally with Google's open-source ADK.
Planned
Lesson 14

AI-assisted testing

Generate, run, review, and let failures guide the fix - better coverage without blindly trusting generated tests.
Planned
Lesson 15

AI code review & issue detection

Use AI to catch the serious issues in review - real bugs, security, and risky changes.
Planned
Lesson 16

Documentation from sprint changes

Generate release notes and docs straight from a sprint's commits and pull requests.
Planned

Why "from scratch"?

Most tutorials teach you to glue frameworks together. This course does the opposite: you write the chunker, the retriever, the grounding prompt, and the provider abstraction yourself - a few dozen lines each. Once you understand the primitives, every framework (LangChain, LlamaIndex, LangGraph) becomes obvious, because you already know what it automates.

How each lesson works

Every lesson is an interactive step-by-step slider. Each step explains what you're building and why, gives you the exact command to type, and shows the code. Use the ← / → arrow keys, the dots, or the buttons to move between steps. Any step is deep-linkable, so you can share a link straight to a specific point.

Setup, PDFs & languages

Runs with the language toolchains directly - no Docker. One-time setup and per-lesson dependencies for Linux, macOS, and Windows are in the install guide. The course is polyglot: Python is the reference today, with Node.js and C# opt-in per lesson (./run -l 1 --lang node).

Every lesson with a written guide also has a printable PDF - open a menu to grab one:

Lessons 1-10
Lesson 1 · RAG from scratch Lesson 2 · MCP servers Lesson 3 · Hybrid retrieval & reranking Lesson 4 · RAG safety & prompt injection Lesson 5 · RAG evaluation & regression testing Lesson 6 · Repo-aware AI assistant Lesson 7 · Rebuild RAG with LangChain Lesson 8 · A stateful agent with LangGraph Lesson 9 · Ollama + function calling Lesson 10 · Jev and System One models Lesson 10 · slide deck
Roadmap 11-16
Lesson 11 · Microsoft Semantic Kernel Lesson 12 · AWS Bedrock Agents Lesson 13 · Google AI Development Kit Lesson 14 · AI-assisted testing Lesson 15 · AI code review & issue detection Lesson 16 · Documentation from sprint changes
Begin Lesson 1 → Install guide (PDF)

Who's teaching this

Built and taught by Nik Reljin - a former college educator who likes nothing more than teaching new technologies, and who now helps engineers build with modern AI through team trainings, one-on-one mentoring, talks and workshops, and hands-on courses like this one. More about the author and related work →