AI Fundamentals
Turn scattered curiosity into working AI knowledge. Build a cross-linked knowledge base with Claude Code and Obsidian, then run your day from it.
70+
completed
~30.5h
total time
8
projects
Build an AI Second Brain with Claude Code
Turn a local folder of plain Markdown notes into an AI-readable knowledge base that Claude Code can search, summarize, and write back to.
Automate Your AI Second Brain
Add hooks and scheduled tasks so the second-brain project captures session summaries automatically and runs a daily review with no manual trigger.
Prompt Engineering Fundamentals
Learn Anthropic's documented prompt engineering techniques — clear instructions, multishot examples, chain-of-thought, and XML structuring.
Build a RAG Pipeline from Scratch
Build a working retrieval-augmented generation pipeline using ChromaDB for vector storage and a free local sentence-transformers embedding model.
Fine-tune a Small Language Model
Use LoRA via Hugging Face PEFT to fine-tune a small open-source language model on a custom dataset, on hardware you actually have.
Build an AI Agent with Tool Use
Build a working tool-using agent against the Claude API: define a custom tool, handle the tool_use/tool_result loop manually, and add guardrails.
Evaluate LLM Outputs Like an Engineer
Build a small but real evaluation suite for an LLM-powered feature: define success criteria, write graded test cases, and implement scoring.
Deploy Your AI App to Production
Wrap a Claude-powered feature in a production-shaped FastAPI service — async client, timeouts, streaming, structured logging, health checks.