#4949th of 100 in Learning and cookbooks
ai-system-design-guide
Markdown guide to AI system design, RAG, agents and interview prep
- Stars
- 4.3k
- License
- MIT
- Last commit
- Nov 2026
304 on 22 Apr 20264,258 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A text-only reference with chapters on LLM internals, RAG, agentic systems, MCP and A2A, inference, evaluation, security and model pricing. It includes a 193-question interview bank, answer frameworks and 15 case studies with diagrams. There is no code to run; the content is read on GitHub or at aidaddy.tech.
Who it is for: Engineers preparing for AI interviews or designing production LLM systems
Strengths
- Numbered chapters cover RAG, agents, MCP/A2A, evals, gateways and voice agents
- 193-question interview bank with answer frameworks and a worked mock transcript
- Case studies with diagrams, e.g. multi-tenant SaaS and eval-gated CI/CD
- MIT-licensed, with a searchable online version at aidaddy.tech
Weaknesses
- Documentation only; the README mentions no runnable code or notebooks
- Model names, prices and benchmark scores date quickly and need constant upkeep
- README promotes the author's paid mock interviews and mentorship
- Model recommendations are single-author opinion and hard to verify independently
What it needs
- no GPU
Also in Learning and cookbooks
See all 100| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 91 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 83 out of 100 |
| 3 | rag_techniquesCollection of 42 runnable notebooks implementing RAG techniques | 82 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 82 out of 100 |
| #5 | ai-for-beginners24-lesson AI curriculum with notebooks in PyTorch and TensorFlow | 81 out of 100 |