Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

ai-engineering-from-scratch

ai-engineering-from-scratch• Pinned

ai-engineering-from-scratch: Implement model internals, retrieval pipelines, and agent runtimes.

What problem it solves

Learners need a practical path from AI engineering fundamentals to tested systems rather than isolated API examples. The curriculum is structured to make model internals, retrieval pipelines, agent runtimes, evaluation, and failure inspection understandable through runnable code and retained evidence.

Key features

  • Structured AI engineering curriculum — The curriculum spans mathematical foundations through model internals, LLM systems, agents, tools, protocols, and production delivery. It contains 542 lessons across 20 phases, with material in Python, TypeScript, Rust, and Julia.

    Source: README

  • Multiple learning routes — Learners can begin with model foundations, LLM systems, or agents and delivery, or choose a goal-specific path. A placement quiz maps existing knowledge to a starting phase and creates a personalized study plan.

    Source: README, learning-paths

  • Web, coding-agent, and local learning — Completed lessons can be opened on the website, studied with a skill-capable coding agent, or run locally. The tutor provides interactive lessons, quizzes, progress records, and topic routing.

    Source: README, skills

  • Projects with staged validation — Three projects provide staged starters, reference implementations, and local graders. Learners implement retrieval evaluation, agent trace debugging, and tool-call policy enforcement, then retain reproducible outputs and regression reports.

    Source: README, projects

  • Evidence-based lesson workflow — Each lesson follows a consistent workflow: read, build, run, and keep evidence. The curriculum asks learners to save commands, working directories, exit codes, meaningful output, and changed or produced artifacts.

    Source: README

Quick start

Copied verbatim from the project's README.

git clone https://github.com/rohitg00/ai-engineering-from-scratch.git
cd ai-engineering-from-scratch
python3 phases/00-setup-and-tooling/01-dev-environment/code/verify.py --route beginner
python3 phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py
npx skills add rohitg00/ai-engineering-from-scratch

Who it may suit

Inference: may suit programmers and engineers who want to understand AI systems beyond API calls, including beginners, Python developers, ML learners, and engineers working with LLMs, agents, MCP, or Agent Skills.

Topics to discuss

  • Which learning route is most effective for different levels of prior programming and AI experience?

  • How should learners balance implementation exercises, evaluation projects, and conceptual lessons?

  • What evidence should communities expect when sharing solutions, regressions, and project artifacts?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/rohitg00/ai-engineering-from-scratch#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/rohitg00/ai-engineering-from-scratch

Comments

…