# ombharatiya/ai-system-design-guide

AI system design guide for engineers building production AI systems and evals.

Repository: https://github.com/ombharatiya/ai-system-design-guide
Canonical: https://ross.abutalabs.com/products/ai-system-design-guide
Homepage: https://www.aidaddy.tech
License: MIT
License Family: permissive
Topics: agentic-ai, agentic-workflow, artificial-intelligence, aws, azure, claude, gemini, gen-ai, interview-questions, llm, machine-learning, natural-language-processing, open-ai, rag, system-design-interview, evals, ai, interview, ai-jobs, forward-deployed-engineer
Last push: 2026-08-15T17:36:14+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 35, longevity 18
- inputs: {"age_days": 260, "days_push": 18, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2885, forks 579 (observed 2026-08-28T04:07:27.450712+00:00)

## What it is
An open-source, continuously updated guide to AI system design covering RAG architectures, LLM engineering, agentic AI, MCP/A2A protocols, and evaluation. It serves as both a production reference and an interview preparation resource with a 128-question interview bank.

## Use cases
- prepare for AI system design interviews
- learn how to design RAG architectures for production
- understand agentic AI workflows and MCP protocols
- study LLM evaluation and model selection patterns
- review staff-level AI engineering interview questions
- learn production patterns for building AI systems

## When to choose
- you are preparing for AI/ML engineering or forward-deployed engineer interviews
- you want a curated, continuously updated reference on production AI system design
- you need practical patterns for RAG, agents, and evals in one place

## When to avoid
- you need executable code or a working framework rather than written guidance
- you want deep academic treatment of machine learning theory
- you need vendor-specific official documentation

## Facets
- artifact type: learning-resource
- maturity: active
- function: documentation, rag, llm-inference, agent-framework, prompt-engineering
- domain: artificial-intelligence, large-language-models, tutorials, education
- platform: -
- tags: system-design, interview-preparation, ai-engineering, evals, mcp, guide, retrieval-augmented-generation, ai-agents, web-server

## Member repositories
- ombharatiya/ai-system-design-guide (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:27.450712+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:35:24.141224+00:00, confidence not recorded.
  - readme: https://github.com/ombharatiya/ai-system-design-guide (fetched 2026-08-28T04:07:27.450712+00:00, sha 638f1e40bc3c)
  - homepage: https://www.aidaddy.tech (fetched 2026-08-29T09:51:04.825434+00:00, sha b8c8d13cead7)
- Data as of 2026-08-30T08:39:29.467469+00:00.