skills.rest
figulazmi
figulazmiCOMMUNITY
Explore all skills by this author →
GitHub

AI Engineer

Orchestrate RAG, LangChain, and agents for end-to-end AI workflows.

Updated Apr 11, 2026
Search Tags:#architecture#langchain#ai#llm#rag#agents#memory
One-click install
npx skills add https://github.com/figulazmi/token-monitor --skill ai-engineer-figulazmi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AI Engineer
Source: https://github.com/figulazmi/token-monitor/tree/main/.agents/skills/ai-engineer
Command: npx skills add https://github.com/figulazmi/token-monitor --skill ai-engineer-figulazmi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI engineering for building robust, production-grade LLM applications by integrating RAG, LangChain, and agent orchestration to accelerate delivery and reliability.

Core Features & Use Cases

  • RAG Implementation: Build knowledge-grounded Q&A, document assistants, and enterprise search using vector databases, embeddings, and retrieval augmentation.
  • LangChain Architecture: Master the end-to-end LLM app stack including Chains, Agents, Memory, Tools, and observability patterns for scalable workflows.
  • Agent Patterns & Workflows: Implement ReAct, Plan-and-Execute, and Multi-Agent orchestration to automate complex tasks with human-in-the-loop when needed.

Quick Start

Design a document QA architecture using RAG and LangChain.

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-grade RAG application using LangChain?▼

Build production-grade RAG applications with LangChain by orchestrating vector databases, embeddings, and retrieval augmentation to ground LLM responses in your custom document knowledge base for reliable question answering.

What is the best way to implement multi-agent workflows for complex task automation?▼

Implement multi-agent workflows using agent patterns like ReAct and Plan-and-Execute to automate complex tasks, integrating human-in-the-loop checks when needed for reliable orchestration across scalable environments.

How does memory architecture work in LLM chatbots?▼

Memory architecture in LLM chatbots works by managing conversational context through LangChain components, ensuring the model retains session history and previous interactions to maintain coherent multi-turn dialogues.

Do I need vector stores and embeddings for document Q&A systems?▼

You need vector stores and embeddings for document Q&A systems to enable efficient semantic retrieval of relevant text chunks, which grounds the LLM generation process and ensures accurate, context-aware answers.

How do I ensure observability and reliability in LLM applications?▼

Ensure observability and reliability in LLM applications by implementing dedicated testing and monitoring patterns within your LangChain architecture to track agent performance, chain execution, and response quality.

Related Skills

Explore More Software Engineering Skills→
rukikotoorukikotoo
6

rag

Query the econometrics RAG knowledge base to retrieve relevant document chunks.

Community
Intermediate
richardnguyen0715richardnguyen0715

serving-llms-vllm

Deploy and serve LLMs with vLLM, OpenAI-compatible endpoints, and quantization.

Community
Advanced
camoneartcamoneart
5

rag-implementation

Implement RAG systems with vector databases and retrieval strategies.

Community
Advanced
handsomelong922handsomelong922

langchain

Build AI applications with agents, chains, and RAG using LangChain.

Community
Advanced