ai-engineering

Design AI/ML feature architectures with LLM integration and RAG pipelines.

6|1|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/vibbs/company-os --skill ai-engineering-vibbs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ai-engineering
Source: https://github.com/vibbs/company-os/tree/main/.claude/skills/ai-engineering
Command: npx skills add https://github.com/vibbs/company-os --skill ai-engineering-vibbs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill designs the AI/ML architecture for features involving language models, RAG, or agent systems, ensuring integration, cost-efficiency, and safety.

Core Features & Use Cases

  • AI Architecture Design: Creates the AI-specific section of an RFC, covering model selection, integration patterns, prompt engineering, cost modeling, and ethical safeguards.
  • Use Case: When building a new chatbot feature that requires RAG to access a knowledge base, this Skill will define the chunking strategy, embedding model, vector database schema, and prompt design.

Quick Start

Use the ai-engineering skill to design the AI architecture for a new RAG-based feature based on the approved PRD.

Frequently Asked Questions about ai-engineering

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an AI architecture for a RAG pipeline feature?

Designing a RAG pipeline architecture involves defining the chunking strategy, selecting an embedding model, structuring the vector database schema, and engineering the prompts for LLM integration.

What is the best way to optimize LLM integration costs for SaaS features?

To optimize LLM integration costs, structure the AI architecture with cost modeling and efficient model selection to ensure cost-efficiency and safety in AI-assisted SaaS development.

How do I structure an RFC for a new ML or language model integration?

The RFC covers the AI-specific section including model selection, integration patterns, prompt engineering, cost modeling, and ethical safeguards to ensure structured AI component design.

Can I use this approach to mitigate ethical risks in AI-assisted applications?

Yes, ethical risk mitigation is a core component of the AI architecture design, actively addressing the need for structured ethical safeguards within AI-assisted SaaS development.

Does this architecture design work for agent systems and RAG?

Yes, the architecture design explicitly handles features involving language models, RAG pipelines, and agent systems, ensuring proper integration, cost-efficiency, and safety.