Flow Steps

Flow steps are the building blocks of your workflows. After a trigger activates your flow, steps execute in sequence to accomplish your business logic. Each step performs a specific function—from running AI agents to transforming data to making decisions.

Agent-Centric Design: QuivaWorks flows are designed to be agent-first. Start with an AI agent, attach tools (connectors) to it, and add supporting steps as needed. This approach maximizes the intelligence and autonomy of your workflows.

Step Types

Agents

Run AI agents with tools and context

Condition

Branch flows with if/then/else logic

HTTP Request

Call external APIs and services

Map

Transform and iterate over data

Rules

Apply business rules and calculations

Human in the Loop

Add manual approval steps

Delay

Pause workflow execution

Eval

Execute custom JavaScript

Functions

Use utility functions

How Steps Work

Steps execute sequentially after your trigger fires. Each step:

Receives input from the trigger or previous steps
Performs its function (run agent, make decision, transform data, etc.)
Outputs results that subsequent steps can use
Passes control to the next step

Trigger: HTTP POST received
↓
Step 1: Agent analyzes request
↓
Step 2: Condition checks agent decision
↓ (if approved)
Step 3: HTTP Request sends to CRM
↓
Step 4: Map formats response
↓
Return: Success message

Trigger: New customer inquiry
↓
Step 1: Agent (with tools)
  - Searches knowledge base
  - Checks order history
  - Accesses product catalog
  - Makes decision
↓
Step 2: Condition on agent decision
↓ (if escalate)
Step 3: Human in the Loop approval
↓ (if approved)
Step 4: Agent sends response

The Agent-Centric Approach

Start with agents, not automation. Traditional workflow tools force you to map out every step explicitly. QuivaWorks is different—you delegate work to intelligent agents and let them figure out the details.

Traditional Approach (Step-by-Step)

Receive customer question
Search knowledge base
If found: Format answer
If not found: Search help docs
If found: Format answer
If not found: Create support ticket
Send response

Problem: Breaks when anything unexpected happens

Agent-Centric Approach

1. Receive customer question
2. Agent (with tools):
   - Knowledge base connector
   - Help docs connector
   - Ticketing system connector
   → Agent decides best approach
3. Send response

Benefit: Agent adapts to any scenario

Best Practice: Let agents handle complexity. Only add additional steps (Conditions, Maps, HTTP Requests) when you need:

Explicit branching logic that you control
Data transformation before/after agents
Direct API calls without agent interpretation
Business rules that must be enforced

Common Step Patterns

Agent → Condition → Action

Let agent make decision, branch based on outcome, take action.

Agent analyzes customer request
↓
Condition: If agent.decision = "refund"
↓ (true)
HTTP Request: Process refund

Use when: Agent provides intelligence, but you need explicit control over outcomes.

Map → Agent → Map

Transform data before agent, process with agent, format after.

Map: Extract relevant fields
↓
Agent: Analyze and respond
↓
Map: Format for external system

Use when: Agent needs clean input or output needs specific structure.

Rules → Agent

Evaluate business rules first, then let agent handle complexity.

Rules: Check eligibility criteria
↓
Condition: If eligible
↓ (true)
Agent: Process application

Use when: Hard requirements must be met before agent processes.

Agent → Human in Loop → Agent

Agent proposes, human approves, agent executes.

Agent: Analyze request and propose solution
↓
Human in Loop: Review and approve
↓
Agent: Execute approved solution

Use when: High-stakes decisions need human oversight.

HTTP → Map → Agent

Fetch external data, transform it, let agent process.

HTTP Request: Get customer data from CRM
↓
Map: Extract relevant fields
↓
Agent: Personalize response using data

Use when: Agent needs context from external systems.

Delay → Agent

Wait for time-based conditions, then process with agent.

Delay: Wait 24 hours
↓
Agent: Follow up on unanswered inquiry

Use when: Time-based workflows or retry logic.

Step Best Practices

Start Simple

Begin with one agent. Add steps only when needed. The simpler your flow, the easier to maintain.

Let Agents Decide

Don’t hard-code logic that agents can figure out. Use Conditions only for business-critical branching.

Name Steps Clearly

Use descriptive names: “Analyze Customer Request” not “Agent 1”. Makes flows self-documenting.

Test as You Build

Test each step before adding the next. Catch issues early, iterate quickly.

Handle Errors

Add error handling for critical steps. Use Conditions to route failures appropriately.

Use Variables

Reference previous step outputs with variables. Keep data flowing smoothly.

When to Use Each Step

Step Type	Use When	Don’t Use When
Agents	Need intelligence, decision-making, or tool usage	Simple data transformation
Condition	Need explicit branching you control	Agent can decide the path
HTTP Request	Calling external APIs directly	Agent should interpret API data
Map	Transforming data structure or iterating arrays	Agent can handle transformation
Rules	Complex business calculations or eligibility checks	Simple if/then (use Condition)
Human in Loop	High-stakes decisions need approval	Low-risk automated processes
Delay	Time-based workflows or retry logic	Immediate execution needed
Eval	Custom JavaScript logic not available elsewhere	Standard operations (use Functions)
Functions	Common utilities (date, string, array operations)	Complex logic (use Eval or Agent)

Step Variables

Every step outputs data you can reference in subsequent steps. Use the variable syntax to access step outputs:

${step_name.output.field}

Examples:

${agent_1.response}          // Agent's text response
${condition_1.result}        // Condition's boolean result
${http_1.body.data}          // HTTP response body data
${map_1.output}              // Map's transformed output
${rules_1.discount.outcome}  // Rules engine outcome

Learn more about variable syntax in Variable Mapping

Next Steps

Ready to build your flow? Start with the most important step:

Agents

Configure AI agents with tools and context

Condition

Add branching logic to your flows

All Step Types

Explore all available step types

Variable Mapping

Pass data between steps

Get Started

Assistants

Flows

Account Management

Advanced

Flow Steps Overview

Flow Steps

Step Types

Agents

Condition

HTTP Request

Map

Rules

Human in the Loop

Delay

Eval

Functions

How Steps Work

The Agent-Centric Approach

Traditional Approach (Step-by-Step)

Agent-Centric Approach

Common Step Patterns

Step Best Practices

Start Simple

Let Agents Decide

Name Steps Clearly

Test as You Build

Handle Errors

Use Variables

When to Use Each Step

Step Variables

Next Steps

Agents

Condition

All Step Types

Variable Mapping

​Flow Steps

​Step Types

Agents

Condition

HTTP Request

Map

Rules

Human in the Loop

Delay

Eval

Functions

​How Steps Work

​The Agent-Centric Approach

​Traditional Approach (Step-by-Step)

​Agent-Centric Approach

​Common Step Patterns

​Step Best Practices

Start Simple

Let Agents Decide

Name Steps Clearly

Test as You Build

Handle Errors

Use Variables

​When to Use Each Step

​Step Variables

​Next Steps

Agents

Condition

All Step Types

Variable Mapping

Flow Steps

Step Types

How Steps Work

The Agent-Centric Approach

Traditional Approach (Step-by-Step)

Agent-Centric Approach

Common Step Patterns

Step Best Practices

When to Use Each Step

Step Variables

Next Steps