Skip to main content
Once you’ve built or configured an AI agent, there are multiple ways to use it in your applications. This guide covers the different integration patterns available.

​
Integration options

Chat interface

Add conversational AI to your apps with the Chat component

BPMN integration

Trigger agents from workflow nodes

REST API

Call agents programmatically via API

Custom Agent Node

Use agents within Integration Designer workflows

​
Choosing an integration method

MethodBest forUser interaction
Chat interfaceConversational experiences, Q&A, guided assistanceDirect user interaction
BPMN integrationAutomated processing, document handling, decisionsBackground processing
REST APIExternal systems, custom frontends, batch processingProgrammatic access
Custom Agent NodeComplex integrations, multi-step workflowsWorkflow orchestration

​
Common patterns

​
Pattern 1: Conversational assistant

Add a chat interface to help users complete complex tasks with AI guidance. 
User opens app → Chat component loads → User asks questions →
Agent responds → User completes task with guidance
Use cases: Customer support, employee helpdesk, guided form completion

​
Pattern 2: Document processing

Automatically process documents submitted through your application. 
User uploads document → BPMN triggers agent → Agent extracts data →
Data validated → Process continues with extracted data
Use cases: Loan applications, claims processing, onboarding

​
Pattern 3: Decision support

Provide AI-powered recommendations within business processes. 
Process reaches decision point → Agent analyzes data →
Recommendation generated → Human reviews and approves/rejects
Use cases: Credit decisions, risk assessment, fraud detection

​
Pattern 4: Content generation

Generate documents, reports, or communications automatically. 
Process collects data → Agent generates content →
Content reviewed → Document sent/stored
Use cases: Reports, notifications, contracts, summaries

​
Session management

AI agents maintain conversation context through sessions:
ConceptDescription
SessionA conversation thread between user and agent
ContextData and history available to the agent
PersistenceSessions can be saved and resumed
IsolationEach user/process has separate sessions
Sessions are automatically managed when using the Chat component. For BPMN and API integrations, you control session lifecycle explicitly.

​
Data flow

When using agents, data flows through several stages:
1

Input preparation

User input, documents, or process data is formatted for the agent
2

Agent processing

The agent processes input using configured workflows and AI models
3

Response generation

Agent produces output: text, structured data, or actions
4

Result handling

Output is displayed to user, stored, or used to continue the process

​
Knowledge bases

Agents can access knowledge bases for context-aware responses:
  • Platform documentation - Built-in FlowX.AI knowledge
  • Custom knowledge bases - Your uploaded documents and data
  • External sources - Connected via MCP integrations

Knowledge Base integration

Learn how to connect knowledge bases to your agents

​
Best practices

Define specific tasks for your agent rather than general-purpose capabilities. Focused agents perform better.
Include relevant process data when calling agents. More context leads to better responses.
Always include fallback paths for when agents fail or return low-confidence results.
Track agent performance and user feedback. Continuously improve prompts and workflows.

Chat interface

Conversational AI integration

BPMN integration

Workflow-based agent usage

Agent Builder

Create custom agents

Config-time agents

Design-time AI assistants
Last modified on February 12, 2026