skills.rest
bugrabilge
bugrabilgeCOMMUNITY
Explore all skills by this author →
GitHub

ai-engineer

Develop LLM applications, RAG systems, and intelligent agents with vector search.

10|2|Updated Mar 10, 2026
Search Tags:#llm#rag#agent#vector search#multimodal ai#production ai#ai engineer
One-click install
npx skills add https://github.com/bugrabilge/bilge-development-kit --skill ai-engineer-bugrabilge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-engineer
Source: https://github.com/bugrabilge/bilge-development-kit/tree/main/skills-extra/ai-engineer
Command: npx skills add https://github.com/bugrabilge/bilge-development-kit --skill ai-engineer-bugrabilge

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill empowers the creation of advanced, production-grade Large Language Model (LLM) applications, including sophisticated Retrieval-Augmented Generation (RAG) systems and intelligent agents, by providing expertise in AI architecture, vector search, and multimodal integration.

Core Features & Use Cases

  • LLM Application Development: Design and implement LLM features, chatbots, and AI-powered applications.
  • Advanced RAG Systems: Build robust RAG pipelines with optimized retrieval, embedding, and reranking.
  • Agent Orchestration: Develop complex agent workflows using frameworks like LangChain and CrewAI.
  • Multimodal AI: Integrate vision, audio, and document AI capabilities.
  • Use Case: Develop a customer-facing AI assistant that can understand product documents, answer complex user queries using RAG, and escalate issues to specialized agents when necessary.

Quick Start

Use the ai-engineer skill to build a production RAG system for enterprise knowledge base with hybrid search.

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 production-ready RAG system with hybrid search for an enterprise knowledge base?▼

To build a production-ready RAG system, you design robust pipelines with optimized retrieval, embedding, and reranking. This approach enables enterprise knowledge bases to handle complex queries using vector search and advanced agent orchestration.

Can I integrate multimodal AI capabilities like vision and audio into LLM applications?▼

Yes, you can integrate multimodal AI capabilities into LLM applications. This involves combining vision, audio, and document AI processing within your architecture to allow models to understand and generate content across multiple data formats.

What is the best way to manage models and ensure AI safety in production LLM applications?▼

The best way to manage models and ensure AI safety in production LLM applications is by implementing enterprise AI integrations and strict model management protocols. This maintains operational integrity and mitigates risks across deployed intelligent agents.

Does this approach support developing customer-facing AI assistants that escalate issues to specialized agents?▼

Yes, this approach supports developing customer-facing AI assistants capable of understanding product documents and answering queries using RAG. It specifically includes architecting workflows to escalate complex issues to specialized agents when necessary.

Related Skills

Explore More Software Engineering Skills→
qodex-aiqodex-ai
39

rag-agent-builder

Build RAG applications with vector databases, embeddings, and retrieval strategies.

Official
Advanced
davidrrowleydavidrrowley

azure-monitor-opentelemetry-exporter-java

Export OpenTelemetry traces, metrics, and logs from Java applications to Azure Monitor.

Community
Intermediate
bobmatnycbobmatnyc
3

langchain-framework

Build and orchestrate LLM-powered applications with LangChain.

Community
Intermediate
HemantSudarshanHemantSudarshan

rag-implementation

Implement production RAG pipelines from document ingestion to generation.

Community
Advanced