> ## Documentation Index > Fetch the complete documentation index at: https://microstrate-1133-notifications-prefs.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Flows Overview > Build intelligent workflows with AI agents, automation, and business logic # Understanding Flows Flows are the foundation of automation in QuivaWorks. They allow you to build intelligent workflows that combine AI agents, business logic, data transformation, and integrations to automate complex business processes. ## What is a Flow? A flow is a sequence of connected steps that execute in response to a trigger. Think of it as a recipe for automation: * **Triggers** start your flow (webhooks, schedules, form submissions, etc.) * **Steps** perform actions (run AI assistants, make decisions, transform data, call APIs) * **Connections** pass data between steps using variable mappings Flow Architecture

## Core Concepts ### Agent-Centric Design QuivaWorks flows are designed around **AI agents** as the primary intelligence layer. While traditional automation requires you to program every step, agent-centric flows allow you to: * Define what you want to accomplish, not how to accomplish it * Let agents make intelligent decisions based on context * Handle exceptions and edge cases naturally through reasoning * Use tools and connectors dynamically based on the situation **Traditional Automation**: If email contains "refund" → Send to refunds team. If email contains "technical" → Send to support team. Else → Send to general inbox. **Agent-Centric Flow**: Trigger on new email → Agent reads email, understands intent, checks order history, applies policies, and either resolves immediately or routes to appropriate team with context. The agent handles nuance, multiple topics, and exceptions without explicit programming. ### Trigger → Agent → Tools Pattern The optimal flow pattern in QuivaWorks: 1. **Trigger** - Start the flow (form submission, schedule, webhook, etc.) 2. **Agent** - Process the trigger with intelligence and reasoning 3. **Tools** - Give the agent access to your data and systems (connectors) This pattern allows maximum flexibility while maintaining simplicity. Choose how your flow starts (form, API, schedule, etc.) Define the agent's role and capabilities Connect your CRM, database, APIs, and other services Activate your flow and let it run ## Flow Components ### Triggers Triggers define how and when your flow starts. Every flow needs at least one trigger. Buttons, forms, and chat windows embedded in your website Custom API endpoints to trigger flows programmatically Receive events from external applications Run flows on a recurring schedule Trigger when documents are uploaded Process incoming emails automatically Real-time message processing (Advanced mode) Complete trigger reference ### Steps Steps are the building blocks of your flow. They perform actions, make decisions, and transform data. AI agents that reason, use tools, and make decisions Branch your flow based on logic and rules Call external APIs and services Transform and reshape data structures Apply business logic and calculations Request human approval or input Use utility functions and storage operations Complete steps reference ## Common Flow Patterns ### Customer Service Automation ``` Email Trigger → Customer Service Agent → - Tool: Search Knowledge Base - Tool: Get Order History - Tool: Apply Return Policy → Condition → - Can Resolve → Send Response - Needs Human → Human in the Loop ``` ### Lead Qualification ``` Form Trigger → Lead Qualification Agent → - Tool: Search CRM - Tool: Company Data API - Tool: Scoring Rules → Condition → - Qualified → Add to CRM + Notify Sales - Not Qualified → Add to Nurture Campaign ``` ### Content Generation ``` Schedule Trigger → Content Creation Agent → - Tool: Get Brand Guidelines - Tool: Get Customer Data - Tool: Get Performance Metrics → Map (Format for Channels) → → Multiple HTTP Requests → - Post to Social Media - Send to Email Platform - Update Content Calendar ``` ### Invoice Processing ``` Upload Trigger → Invoice Processing Agent → - Tool: Extract Data (OCR) - Tool: Get Purchase Orders - Tool: Validate Against Rules → Condition → - Valid → Approve + Update ERP - Invalid → Human in the Loop + Flag Issues ``` ## Flow Execution ### Response Modes Flows can run in two modes: The trigger waits for the entire flow to complete before responding. Best for: * API endpoints that need to return results * Form submissions that show confirmation * Chat interactions that need immediate responses The trigger responds immediately and the flow runs asynchronously. Best for: * Long-running processes * Scheduled workflows * Email processing * Webhook handlers ### Variable Mapping Data flows between steps using **variable mapping**. Each step can access: * Trigger data: `$.trigger.email`, `$.trigger.form.name` * Previous step outputs: `$.step_id.response`, `$.step_id.data` * Secrets: `SECRET::API_KEY::` * Transformations: Filters, JSONPath, pipes Learn more about variable mapping in our [Advanced Variable Mapping Guide](/advanced/variable-mapping/overview) ## Building Your First Flow Ready to get started? Follow these guides: Build an agent that handles customer inquiries Qualify and route leads automatically Generate and publish content on schedule Extract and validate data from uploads ## Best Practices Begin with a trigger and a single agent. Test thoroughly. Then add conditions, additional steps, and error handling as needed. Let agents handle reasoning and decision-making. Use condition steps for branching based on clear outcomes. Don't try to program intelligence into conditions. Connect relevant data sources and APIs. The more context an agent has, the better decisions it can make. Add human-in-the-loop steps for critical decisions. Use condition steps to catch errors and provide fallback paths. Use actual customer emails, form submissions, and edge cases when testing. Agents perform best when trained on realistic scenarios. Review flow execution logs regularly. Refine agent instructions and tools based on actual performance. ## Next Steps Learn about all trigger types Explore available step types Deep dive into AI agents Master data transformations Build business logic Flow design patterns ## Need Help? Ask questions and share flows Get help from our team Browse flow templates