signalGitHub Trending2026-09-26
rohitg00/ai-engineering-from-scratch
This open-source AI engineering curriculum offers 523 lessons across 20 phases, totaling about 342 hours, and covers Python, TypeScript, Rust, and Julia. It aims to close the gap between student AI usage (84%) and professional preparedness (18%) by having every lesson produce a reusable artifact such as a prompt, skill, agent, or MCP server. The curriculum is free, MIT-licensed, and has attracted over 114,000 readers with nearly 182,000 page views in the last 30 days.
- for who
- Aspiring AI engineers and developers who want a hands-on, end-to-end curriculum from foundations to advanced agent and MCP systems.
- why now
- 84% use AI tools, 18% feel prepared: this free curriculum closes that gap now.
- what changes
- Learners move from passive AI tool usage to actively building and shipping AI systems with proven, evidence-based lessons.
- to do
- Clone the repository and run the provided verification and vector exercises to generate your first learning evidence.
key points
- 523 lessons, 20 phases, ~342 hours, covering Python, TypeScript, Rust, Julia
- 84% of students use AI tools, but only 18% feel prepared; curriculum closes that gap
- Every lesson ships a reusable artifact: prompt, skill, agent, or MCP server
#ai education#open source curriculum#agent engineering
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source