> ## Documentation Index > Fetch the complete documentation index at: https://docs.orq.ai/llms.txt > Use this file to discover all available pages before exploring further. # Cookbooks and tutorials > Step-by-step tutorials for building AI applications with Orq.ai. Covers RAG chatbots, text-to-SQL, PDF extraction, and multi-agent systems. ##    Common Architectures Proven implementation patterns for building AI applications, from simple LLM integrations to complex multi-agent systems. > **[Simple Deployment](/ai-studio/cookbooks/common-architecture/simple-deployment.md)** > > The most straightforward way to integrate LLM calls through **Orq.ai** as an AI Gateway. > **[Chatbot Architecture](/ai-studio/cookbooks/common-architecture/chatbot.md)** > > Build conversational AI with memory, context awareness, and intelligent escalation. > **[Simple RAG](/ai-studio/cookbooks/common-architecture/simple-rag.md)** > > Ground LLM responses in your knowledge base for accurate, context-aware answers. > **[Advanced RAG](/ai-studio/cookbooks/common-architecture/advanced-rag.md)** > > Add reranking, hybrid search, and query optimization to your RAG system. > **[AI Agent](/ai-studio/cookbooks/common-architecture/ai-agent.md)** > > Build autonomous agents with tool calling, memory, and multi-agent coordination. > **[Agents Framework Guide](/ai-studio/cookbooks/common-architecture/agents-framework-guide.md)** > > Integrate **Orq.ai** with LangGraph, CrewAI, and AutoGen for observability and control. > **[Advisor and Sidekick](/ai-studio/cookbooks/common-architecture/advisor-and-sidekick.md)** > > Run a cheap primary model in **Orq.ai** and pay for a stronger one only at the step that needs it. > **[AI Gateway vs Config Management](/ai-studio/cookbooks/common-architecture/gateway-vs-config.md)** > > Understand the differences between the two core integration patterns. ##    Chatbots & AI Apps End-to-end guides for building production chatbots, conversational AI, and multi-agent applications. > **[Chat History](/ai-studio/cookbooks/chatbots/maintaining-history-with-a-model.md)** > > Maintain conversation history across messages for stateful LLM interactions. > **[Multilingual FAQ Bot](/ai-studio/cookbooks/chatbots/multilingual-faq-bot.md)** > > Build a multilingual FAQ chatbot with RAG and dynamic language routing. > **[Intent Classification](/ai-studio/cookbooks/chatbots/intent-classification.md)** > > Categorize user queries for chatbots, support, and task automation. > **[Lovable Integration](/ai-studio/cookbooks/chatbots/lovable-integration.md)** > > Build RAG-powered FAQ bots using prompt-based development without a backend. > **[Multi-Agent HR System](/ai-studio/cookbooks/chatbots/agents-API.md)** > > Build a multi-agent system with specialized agents, memory, and knowledge bases. > **[Insurance Claims via MCP](/ai-studio/cookbooks/chatbots/insurance-claims-mcp-cookbook.md)** > > Build and compare a single-agent vs multi-agent claims system from your coding assistant via MCP. > **[Speech-to-Text and Text-to-Speech](/ai-studio/cookbooks/chatbots/voice-loop-transcription-and-speech.md)** > > Compose transcription and text-to-speech around a model call to build a voice-in, voice-out loop. ##    Data & Extraction Use AI to extract structured data from unstructured documents, images, and natural language inputs. > **[PDF Extraction](/ai-studio/cookbooks/data-extraction/pdf-extraction.md)** > > Extract structured data from PDF invoices using vision models. > **[Receipt Extraction](/ai-studio/cookbooks/data-extraction/receipt-extraction.md)** > > Process receipt images into structured JSON with vendor names, amounts, and dates. > **[Text-to-SQL](/ai-studio/cookbooks/data-extraction/text-to-sql.md)** > > Transform natural language into SQL queries for non-technical database access. ##    Evaluation & Safety Test, evaluate, and red-team your LLM deployments to ensure quality, reliability, and security. > **[Parallel Evaluations](/ai-studio/cookbooks/evaluation-safety/evaluator-q.md)** > > Run evaluations in parallel at scale using evaluatorq. > **[Agent Simulation](/ai-studio/cookbooks/evaluation-safety/agent-simulations.md)** > > Drive an **Agent** through multi-turn conversations with personas, then replay them to prove a fix worked. > **[Red Teaming](/ai-studio/cookbooks/evaluation-safety/improve-agent-with-red-teaming.md)** > > Attack an **Agent** with generated adversarial prompts, then fix what leaks. > **[Automate Evals with Claude Code](/ai-studio/cookbooks/evaluation-safety/automate-evals-and-observability-with-claude-code.md)** > > Drive the full evaluator optimization loop from the terminal using Claude Code + **Orq.ai** MCP. > **[Align Evaluators](/ai-studio/cookbooks/evaluation-safety/align-evaluators.md)** > > Find where an LLM-as-a-judge **Evaluator** disagrees with human reviewers and rewrite its prompt via MCP. > **[Benchmark Models with Model Arena](/ai-studio/cookbooks/evaluation-safety/model-arena.md)** > > Run a real head-to-head model benchmark and read a statistically defensible ranking instead of a public leaderboard. ##    Integrations & Tooling Connect **Orq.ai** with your existing tools, workflows, and third-party infrastructure. > **[Chaining Deployments](/ai-studio/cookbooks/integrations-tooling/chaining-deployments.md)** > > Chain multiple LLM deployments and run evaluators across multi-step workflows. > **[Prompt Manager](/ai-studio/cookbooks/integrations-tooling/prompt-manager.md)** > > Fetch deployment configurations at runtime while keeping control over your infrastructure. > **[Capturing Feedback](/ai-studio/cookbooks/integrations-tooling/capturing-feedback-with-orq.md)** > > Implement structured user feedback to improve LLM responses over time. > **[LangGraph + Orq.ai](/ai-studio/cookbooks/integrations-tooling/integrate-langgraph-with-orq.md)** > > Slot **Orq.ai** under an existing LangGraph agent for model routing, RAG, and traces. ##    Learn Reference guides and conceptual explainers for LLM concepts, prompt engineering, and platform features. > **[LLM Glossary](/ai-studio/cookbooks/learn/llm-glossary.md)** > > Definitions for 200+ LLM, LLMOps, and prompt engineering terms. > **[Prompt Engineering Guide](/ai-studio/prompts/prompt-engineering-guide.md)** > > Best practices for LLM optimization, structured prompts, and consistent outputs. > **[Prompt Templating](/ai-studio/prompts/prompt-templating.md)** > > Complete reference for Jinja and Mustache templates in deployments and experiments. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.