> ## 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 in FlowX > AI agents for every stage - config-time agents help you build apps faster, while business agents power intelligent experiences for your end-users. AI Platform · FlowX.AI AI agents for every stage. FlowX AI Platform provides intelligent agents across your entire application lifecycle. Whether you're building apps or running them, AI agents accelerate your work and enhance user experiences. [Explore Agent Builder](https://docs.flowx.ai/6.x/ai-platform/agent-builder/overview.md) [Developer Agentic Harness](https://docs.flowx.ai/6.x/ai-platform/developer-agentic-harness.md) 01 · Agent types ## Two types of AI agents FlowX provides agents for different stages of your application lifecycle: 01 · config time FlowX Designer Config-time agents help you build processes, UIs, and business rules. 02 · build Agent Builder · Marketplace Create custom business agents or start from pre-built accelerators. 03 · runtime Business agents Run inside your apps, serving your customers and employees. 01 Config-time agents Help you build apps faster. The Developer Agentic Harness in FlowX Designer plans and carries out the changes you describe: processes, UIs, data models, and business rules. Used by designers, developers, analysts. 02 Business agents Power your end-user experiences. AI agents that run inside your applications, interacting with customers and employees to automate tasks and provide intelligent assistance. *** 02 · Config time ## Config-time agents In FlowX Designer, you build with the [Developer Agentic Harness](https://docs.flowx.ai/6.x/ai-platform/developer-agentic-harness.md). Press **⌘K** (**Ctrl+K** on Windows and Linux), or select **Build with AI** in the Designer header, to open the agent rail. You describe a change to your app, and the agent plans it and carries it out on a dedicated branch for your review. [Agent Builder](https://docs.flowx.ai/6.x/ai-platform/agent-builder/overview.md), covered below, builds business agents that run inside your apps. *** 03 · Runtime ## Business agents Agents that power intelligent experiences for your end-users. You have two options: ### FlowX accelerators Pre-built business agents created by FlowX, ready to deploy: * Industry-specific solutions for banking, insurance, and more * Tested and optimized for common use cases * Deploy immediately or customize to your needs ### Custom agents Use **Agent Builder** to create AI agents tailored to your specific business processes: documentsExtract data from forms, contracts, and statements.contentCreate personalized communications and reports.decisionsAnalyze data and provide recommendations.conversationsBuild chat-based customer interactions. [→ Agent Builder Create custom AI agents for your specific business needs.](https://docs.flowx.ai/6.x/ai-platform/agent-builder/overview.md) *** 04 · Integrate ## Integrating agents into apps Once you have business agents (custom or from marketplace), integrate them into your applications: [01 Chat interface Conversational UI for end-users.](https://docs.flowx.ai/6.x/ai-platform/using-agents/chat-interface.md) [02 BPMN integration Trigger agents from workflows.](https://docs.flowx.ai/6.x/ai-platform/using-agents/bpmn-integration.md) [03 API access Programmatic integration.](https://docs.flowx.ai/6.x/ai-platform/integrations.md) *** 05 · Security ## Enterprise security All FlowX AI agents are built for banking-grade security: | Security feature | Description | | - | - | | **Zero-trust model** | All components authenticate each other, preventing unauthorized access | | **Input/output scanning** | Detect prompt injection, ban sensitive substrings, sanitize outputs | | **Custom fine-tuned models** | Purpose-built models with curated data for each use case | | **Human oversight** | Human-in-the-loop controls for ethical decision-making | *** 06 · Data protection ## Personal data protection FlowX ensures personal data never reaches AI models by design through controlled data ingestion, deterministic workflows, and encryption options. ### Data ingestion paths Personal data enters the platform through three channels: | Channel | Data handling | | - | - | | **Forms / UIs** | Input data mapped directly to the process data model | | **3rd party APIs** | API responses mapped to the process data model | | **Documents** | Structured docs (Word, Excel) have fields mapped automatically; unstructured docs require OCR extraction with optional human verification | > [!NOTE] > > For unstructured documents containing sensitive data, a human operator can verify extracted data accuracy before it's mapped to the data model. ### Data storage All ingested data ends up in **data models** - JSON collections stored in FlowX databases: * Data models are only accessible to deterministic business process steps * Process logic controls when, how, and which data is sent to AI steps * This ensures **no personal data is sent to AI by design** ### Protection options | Option | Description | | - | - | | **Database encryption** | Encrypt data at rest using database capabilities (e.g., pgcrypto in PostgreSQL) - prevents administrator access to business data | | **Sensitive data masking** | Mark specific data model fields as sensitive to hide them in UIs and console outputs | | **Custom guardrails** | Additional guardrails can be enforced in AI workflows | > [card] [Data Model](https://docs.flowx.ai/6.x/docs/building-blocks/process/data-model.md) > > Learn about process data models > [card] [Sensitive Data](https://docs.flowx.ai/6.x/docs/building-blocks/process/data-model.md#sensitive-data) > > Configure sensitive data masking *** 07 · Reliability ## Hallucination prevention | Technique | Purpose | | - | - | | **RAG** | Ground responses in reliable external data sources | | **Multi-agent architecture** | Dedicated agents for specific tasks with specialized processing | | **Structured outputs** | Enforce JSON outputs for consistent, parseable responses | | **Model evaluation** | Continuous testing to find optimal models for each task | | **Prompt tuning** | Task-specific prompts to enhance accuracy and relevance | *** 08 · Resources ## Related resources [01 Chat component Technical reference for chat integration.](https://docs.flowx.ai/6.x/ai-platform/chat-component.md) [02 AI integrations Connect agents to knowledge bases and external systems.](https://docs.flowx.ai/6.x/ai-platform/integrations.md) [03 AI Platform setup Configure AI Platform for your environment.](https://docs.flowx.ai/6.x/setup-guides/ai-platform-setup.md) [04 Using agents Integration patterns and best practices.](https://docs.flowx.ai/6.x/ai-platform/using-agents/overview.md) [05 Research Open-source guardrails, open models, and the paper series.](https://docs.flowx.ai/6.x/ai-platform/research.md) ## Related topics - [FlowX.AI Designer](https://docs.flowx.ai/6.x/docs/flowx-designer/overview.md) - [FlowX.AI CMS](https://docs.flowx.ai/6.x/docs/platform-deep-dive/core-extensions/content-management/content-management.md) - [FlowX.AI documentation](https://docs.flowx.ai/6.x/docs/introduction.md) - [FlowX.AI Scheduler](https://docs.flowx.ai/6.x/docs/platform-deep-dive/core-extensions/scheduler.md) - [FlowX.AI Engine](https://docs.flowx.ai/6.x/docs/platform-deep-dive/core-components/flowx-engine.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.