ai-engineer-notebooks

Overview of ai-engineer-notebooks

What it is

A collection of hands-on, framework-free Colab notebooks covering the applied-LLM stack for the AI Engineer / Forward Deployed Engineer (FDE) skill set. Topics include model APIs, structured output, tool calling, RAG, evals, agents, fine-tuning, security, LLMOps, and customer craft. All notebooks run on the free Groq API (no credit card required).

Key features

• Framework-free by design: you write agent loops, RAG, and evals from raw API calls before using any wrapper.
• Evals are the spine: the “measure before you tune” habit is introduced early and reinforced throughout.
• Free to run end to end: everything works on the free Groq API; LoRA fine-tuning and self-hosted serving have optional Colab-GPU appendices verified on a real T4.
• Real case studies: three end-to-end scenarios (support assistant debugged in production, pipeline-vs-agent cost showdown, red-team robustness benchmark).
• OpenAI-compatible throughout: every pattern transfers directly to OpenAI and (with small changes) Anthropic.

Use cases

Backend or full-stack engineers transitioning into AI Engineer, Forward Deployed Engineer (FDE), Applied AI, or Solutions Engineer (AI) roles. The notebooks assume you can ship production code and want to add the applied-model layer.

Getting started

Each notebook is self-contained: it installs its own dependencies and reads API keys from Colab secrets. No global setup is required. See the repository README for the full learning order and links to individual notebooks.

License and pricing

License: MIT. Pricing: open source (free).

Based on the project's public README and repository metadata.