Learn AI, hand-reviewed.

Curated by editors who have built agents in production. Free + paid picks ordered by what we'd recommend to a friend.

The shortlist for learning to prompt LLMs in 2026 — separated by whether you're a developer or not.

The right courses to take if you're going to fine-tune, self-host, or seriously evaluate LLMs.

The LangChain learning path — official short courses plus deeper paid alternatives.

Get 3-10x faster on Cursor, Claude Code, and the rest of the 2026 AI coding stack.

RAG looks easy in a demo and fails in production. These are the courses that teach the failure modes.

MCP is becoming the lingua franca of AI agent integrations. These are the right courses to learn it.

n8n is the open-source automation tool of choice for AI workflows in 2026. These are the right courses to learn it.

AI fluency without Python. The right courses for non-technical leaders who need to evaluate vendors and scope projects.

Evaluation is the difference between an AI demo and an AI product. These are the right courses to learn it.

Vibe coding — the AI-driven workflow Karpathy named in 2025 — has become the dominant way working engineers ship in 2026. Here's where to learn it.

"AI Engineer" replaced "ML Engineer" as the dominant 2026 job title. Here's the curriculum that actually gets you hired.

Fine-tuning is the most over-recommended and under-understood pattern in applied LLMs. These are the courses that teach when (and when not) to do it.

AI safety has moved from niche concern to baseline engineering hygiene. These are the courses we recommend.