- Knowledge Bases - Ground responses in your documents using RAG
- MCP servers - Connect external tools via Model Context Protocol
- REST APIs - Call any HTTP endpoint
- FlowX Database - Query and store structured data
- Kafka - Event-driven integrations
What can you build?
Agent Builder allows you to create specialized AI agents that can:Process documents
Extract, validate, and analyze data from various document types
Understand content
Perform sentiment analysis, topic modeling, and named entity recognition
Generate content
Create summaries, translations, and complete documents
Analyze images
Recognize objects, extract text, and understand scenes
Make decisions
Provide risk assessments and compliance checks with full auditability
Key benefits
Business empowerment
- Drag-and-drop interface accessible to non-technical users
- Pre-built templates for common use cases
- Reduced time-to-market for AI solutions
Enterprise-grade features
- Full audit trails and explainable AI decisions
- Integration with existing workflows and systems
- Compliance-ready with regulatory requirements
- Tool call limit — agents are capped at 20 tool calls per run to prevent runaway operations
Available starting with FlowX.AI 5.6.0Custom agents are limited to a maximum of 20 tool calls per execution run. If an agent reaches this limit, it stops processing and returns the result up to that point. Design agents with this limit in mind for complex multi-step workflows.
Core agent categories
Document processing agents
Document processing agents
- Document extraction and validation
- Cross-document consistency checks
- Metadata creation and classification
Analysis agents
Analysis agents
- Sentiment and emotion analysis
- Risk assessment and fraud detection
- Customer behavior analysis for upselling
Generation agents
Generation agents
- Report writing and document completion
- Content summarization and paraphrasing
- Multi-language translation
Getting started
Choose your approach
- Start with pre-built templates for common scenarios
- Create from scratch with custom instructions
Configure your agent
- Define input sources (documents, images, structured data)
- Set processing logic and validation rules
- Configure output formats and destinations
Agent Designer interface
The Agent Designer provides a visual canvas for building AI workflows:| Component | Description |
|---|---|
| Left panel | Available actions and node types to drag onto canvas |
| Canvas | Visual workflow designer where you connect nodes |
| Properties | Configuration panel for selected nodes |
| Test panel | Run tests with sample data |
Related resources
Node types
Learn about Generation, Understanding, Extraction, and Analysis nodes
Use cases
Real-world examples: loan processing, mortgage validation, customer intelligence
Config-time agents
Design-time AI assistants for FlowX Designer
Using agents
Learn how to integrate agents into your apps
Conversational workflows
Build multi-turn chat experiences with session memory and intent routing