ai-engineer

Build and maintain LLM integration and RAG pipelines for the CRPD dashboard.

Updated Mar 27, 2026

Search Tags:#ai #rag #prompt-engineering #knowledge-base #vector-search #llm-integration

Ready to run

npx skills add https://github.com/LinusConradM/test_crpd_dashboard --skill ai-engineer-linusconradm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ai-engineer
Source: https://github.com/LinusConradM/test_crpd_dashboard/tree/main/.claude/skills/ai-engineer
Command: npx skills add https://github.com/LinusConradM/test_crpd_dashboard --skill ai-engineer-linusconradm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The AI Engineer skill defines and maintains the backend systems that empower LLM integration, RAG pipelines, and vector-based search for the CRPD Disability Rights Data Dashboard, enabling deterministic AI features with robust guards.

Core Features & Use Cases

LLM integration for local and cloud deployments, including routing and prompt templates
RAG pipelines with FAISS-based retrieval and knowledge-base construction
Evaluation, monitoring, and secure data handling across embedding generation, prompt engineering, and model coordination

Quick Start

Configure and deploy the LLM integration, RAG pipeline, and vector search components for the CRPD dashboard.

Frequently Asked Questions about ai-engineer

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

FAQPage Schema

How do I build a RAG pipeline with FAISS-based vector search?▼

To build a RAG pipeline with FAISS-based vector search, you need to generate embeddings from your knowledge base and use FAISS to retrieve relevant context for your LLM. This handles embedding generation, knowledge base construction, and prompt engineering.

What is LLM integration and model routing for local and cloud deployments?▼

LLM integration and model routing coordinate requests between local and cloud language models to optimize performance and cost. The system applies prompt templates and routes queries to the appropriate model deployment based on configuration.

How do I implement deterministic prompts and security guardrails for AI backends?▼

Implementing deterministic prompts and security guardrails requires applying strict prompt templates, caching responses, and enforcing error handling rules. This ensures your AI backend produces predictable outputs while maintaining secure data handling across LLM interactions.

Can I use FAISS vector search and local LLMs for a knowledge base?▼

Yes, you can use FAISS vector search with local LLMs to query a knowledge base. The system supports local and cloud LLM usage, allowing you to route queries to local models while using FAISS for retrieval.

What is the best way to evaluate and monitor RAG pipelines and LLM interactions?▼

The best way to evaluate and monitor RAG pipelines is to implement systematic evaluation across embedding generation, prompt engineering, and model coordination. This tracks retrieval accuracy and response quality while maintaining secure data handling.