skills.rest
caobingsheng
caobingshengCOMMUNITY
Explore all skills by this author →
GitHub

ai-engineer

Architect LLM integrations, RAG pipelines, and agent orchestration for production applications.

1|Updated Mar 26, 2026
Search Tags:#architecture#monitoring#production#llm#rag#agents#vector-databases
One-click install
npx skills add https://github.com/caobingsheng/skills --skill ai-engineer-caobingsheng
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-engineer
Source: https://github.com/caobingsheng/skills/tree/main/ai/ai-engineer
Command: npx skills add https://github.com/caobingsheng/skills --skill ai-engineer-caobingsheng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Build production-ready LLM applications, advanced RAG systems, and intelligent agents that scale, integrate, and operate reliably in enterprise environments.

Core Features & Use Cases

  • Production-grade architecture design, multi-model orchestration, vector store integration, safety, observability, and cost controls.
  • Advanced RAG pipelines with multi-stage retrieval, reranking, and context management across disparate data sources.
  • Agent frameworks and orchestration with memory, tool use, and monitoring for end-to-end automation in enterprise workflows.

Quick Start

Configure a production-grade LLM application by wiring data sources, an embedding/RAG pipeline, and an agent orchestration flow, then deploy to production.

Frequently Asked Questions about ai-engineer

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

FAQPage Schema
How do I build production-grade LLM applications with advanced RAG pipelines?▼

Production-grade LLM applications require architecting retrieval-augmented generation pipelines with multi-stage retrieval, reranking, and context management across disparate data sources for enterprise deployment.

What is agent orchestration and how does it work with memory and tool use?▼

Agent orchestration coordinates automated enterprise workflows by integrating memory, tool use, and monitoring to manage end-to-end reasoning and actions within LLM applications.

How do I integrate vector databases for multi-model support in enterprise LLM apps?▼

Integrating vector databases involves configuring embedding pipelines for data ingestion and indexing, enabling multi-model support and retrieval within your enterprise LLM application architecture.

Can I use this approach for monitoring and cost controls in production AI deployments?▼

Yes, this approach supports production AI deployments by implementing safety, observability, monitoring, and cost controls alongside staged rollout and robust error handling.

What's the best way to handle model selection and safety for LLM integrations?▼

The best way to handle model selection and safety for LLM integrations is to architect multi-model orchestration pipelines that satisfy requirements for safety, testing, and deployment in enterprise contexts.

When do I need multi-stage retrieval and reranking in my RAG pipeline?▼

You need multi-stage retrieval and reranking in your RAG pipeline when managing context across disparate data sources, ensuring accurate ingestion, indexing, and retrieval for complex enterprise queries.

Related Skills

Explore More Software Engineering Skills→
patricio0312revpatricio0312rev
5

vector-db-setup

Configure Pinecone, Chroma, pgvector, and Qdrant vector databases for semantic search.

Community
Advanced
Patasse97Patasse97

senior-ml-engineer

Deploy production ML systems with monitoring, drift detection, and cost controls.

Community
Advanced
Hashzin-0Hashzin-0

tool-creator

Create secure MCP tools with Pydantic validation, sanitization, rate limiting, and audit logging.

Community
Advanced
simotasimota
68

Oracle

Design and evaluate LLM-based systems with prompt engineering, RAG, and cost optimization.

Community
Advanced