> ## Documentation Index
> Fetch the complete documentation index at: https://docs.flowx.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI patterns

> Reusable architectural patterns for building AI-powered apps on FlowX.AI.

Patterns are proven solutions to common challenges when building AI apps on FlowX. Each pattern is extracted from production implementations and can be combined to build complex apps.

## Available patterns

> [card] [Agent typologies](https://docs.flowx.ai/6.x/ai-platform/patterns/agent-typologies.md)
>
> The nine recurring agent archetypes behind the FlowX.AI agent catalog, mapped to the nodes that implement them. Start here to pick a shape.

> [card] [Intent classification and routing](https://docs.flowx.ai/6.x/ai-platform/patterns/intent-classification-routing.md)
>
> Use a TEXT\_UNDERSTANDING node to classify user input and route to specialized handlers. The foundation of any conversational AI app.

> [card] [Knowledge base RAG](https://docs.flowx.ai/6.x/ai-platform/patterns/knowledge-base-rag.md)
>
> Ground AI responses in your documents using retrieval-augmented generation with Qdrant vector search and the CUSTOM\_AGENT node.

> [card] [Fan-out extraction](https://docs.flowx.ai/6.x/ai-platform/patterns/fan-out-extraction.md)
>
> Classify documents by type, then route each to a specialized TEXT\_EXTRACTION node with tailored prompts and schemas. Scale to dozens of document types.

> [card] [AI comparison and reconciliation](https://docs.flowx.ai/6.x/ai-platform/patterns/ai-comparison-reconciliation.md)
>
> Compare AI-extracted document data against system-of-record values and generate structured exception reports with match rates and confidence scores.

> [card] [Hybrid AI + business rules](https://docs.flowx.ai/6.x/ai-platform/patterns/hybrid-ai-rules.md)
>
> Combine AI extraction and understanding with deterministic business logic (formulas, eligibility checks, scoring) for auditable decision-making.

> [card] [Session state management](https://docs.flowx.ai/6.x/ai-platform/patterns/session-state-management.md)
>
> Manage conversation history and session state across multi-turn interactions using FlowX Database workflows.

***

## How to use patterns

Each pattern page includes:

* **When to use** — the problem it solves and when to reach for it
* **Architecture** — how the workflow nodes connect
* **Implementation** — key configuration: prompts, schemas, fork conditions
* **Real-world example** — where this pattern appears in the tutorials
* **Variations** — common adaptations

Patterns are building blocks. A typical AI app combines 2-4 patterns:

| App type | Common pattern combination |
| - | - |
| **Conversational advisor** | Intent routing + Knowledge base RAG + Session state + Hybrid AI rules |
| **Document processor** | Fan-out extraction + AI comparison + Hybrid AI rules |
| **Email automation** | Fan-out extraction + AI comparison + Session state |

***

## Multi-agent orchestration

Combining patterns produces **multi-agent apps**: several specialized agents coordinated inside one workflow, each with its own prompt, schema, and model.

* **Router and specialists**: an [intent classification](https://docs.flowx.ai/6.x/ai-platform/patterns/intent-classification-routing.md) agent reads the input and dispatches to specialized handler agents — the foundation of conversational apps.
* **Parallel specialists**: [fan-out extraction](https://docs.flowx.ai/6.x/ai-platform/patterns/fan-out-extraction.md) classifies documents by type and routes each to a dedicated extraction agent with a tailored prompt and schema, scaling to dozens of document types processed in parallel.
* **Agents plus deterministic logic**: [hybrid AI + business rules](https://docs.flowx.ai/6.x/ai-platform/patterns/hybrid-ai-rules.md) places auditable business logic and approval gates between agent steps, so multi-agent output stays governed.

Each agent in the composition can use a [different model](https://docs.flowx.ai/6.x/ai-platform/ai-providers.md), and the whole orchestration is testable with [evaluations](https://docs.flowx.ai/6.x/ai-platform/evaluations.md) per AI node.

***

## Pattern origins

These patterns are extracted from two production-grade FlowX apps:

* **Mortgage advisor** — a chatbot that evaluates loan eligibility across 7 banks using conversational AI, document extraction, and financial calculations
* **Logistics document processor** — an email-triggered pipeline that processes 17 document types from carrier emails, reconciles them against a TMS, and surfaces exceptions for review

See the [Tutorials](https://docs.flowx.ai/6.x/ai-platform/tutorials/overview.md) for full implementations.

***

## Related resources

> [card] [Tutorials](https://docs.flowx.ai/6.x/ai-platform/tutorials/overview.md)
>
> End-to-end implementations using these patterns

> [card] [Node types](https://docs.flowx.ai/6.x/ai-platform/agent-builder/node-types.md)
>
> AI node type reference

> [card] [Chat-driven workflows](https://docs.flowx.ai/6.x/ai-platform/chat-driven-workflows.md)
>
> Multi-turn chat with session memory

> [card] [Using agents](https://docs.flowx.ai/6.x/ai-platform/using-agents/overview.md)
>
> Integration and deployment options


## Related topics

- [AI comparison and reconciliation](https://docs.flowx.ai/6.x/ai-platform/patterns/ai-comparison-reconciliation.md)
- [Hybrid AI + business rules](https://docs.flowx.ai/6.x/ai-platform/patterns/hybrid-ai-rules.md)
- [Knowledge base RAG](https://docs.flowx.ai/6.x/ai-platform/patterns/knowledge-base-rag.md)
- [Session state management](https://docs.flowx.ai/6.x/ai-platform/patterns/session-state-management.md)
- [Agent typologies](https://docs.flowx.ai/6.x/ai-platform/patterns/agent-typologies.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.