Overview

​

What Are Step Workflows?

​

Progressive Disclosure

Letting agents navigate and retrieve data autonomously also enables progressive disclosure—in other words, allows agents to incrementally discover relevant context through exploration. Each interaction yields context that informs the next decision…

​

How It Differs from Monolithic Prompts

​

When to Use Step Workflows

• Complex workflows with multiple stages (verification, data collection, conditional routing)
• State-dependent logic where next actions depend on previously collected information
• Compliance requirements where specific text must be delivered verbatim (legal disclosures, HIPAA notices)
• Testable conversations where you need to verify state transitions and data collection

• Simple single-turn interactions
• Open-ended conversations without clear structure
• Workflows with fewer than 3 distinct stages

​

How It Works

​

Basic Workflow Lifecycle

1. Define the workflow as ordered steps (each with a goal, instructions, optional inputs, and transitions)
2. Agent receives first step: The system automatically presents the first step’s instructions
3. Agent collects inputs: The agent follows step instructions and collects any required information
4. Agent submits the step: The agent calls a special “submit” tool to advance the workflow
5. System validates and transitions: The workflow engine validates inputs, executes any actions, and moves to the next step
6. Repeat until reaching a terminal step (a step with no “next” transition)

​

Visual: Workflow State Machine

​

Visual: Step Lifecycle

​

Key Concepts

​

Steps

• ID: Unique identifier (e.g., COLLECT_NAME)
• Goal: Brief description of what this step accomplishes
• Instructions: Guidance for the agent on what to do
• Inputs: Data to collect (optional, defined as JSON Schema)
• Actions: Operations to perform at lifecycle points (optional)
• Next: Which step(s) to transition to after completion

​

Submit Tool

• Step 1 collects name → submit tool expects {name: string}
• Step 2 collects email → submit tool expects {email: string}

​

Terminal Steps

​

State Management

• Current step inputs: Data collected for the active step
• Workflow variables: Persistent data stored for use across multiple steps
• Completed steps: History of which steps have been submitted

​

Benefits

​

1. Improved Agent Compliance

• Reduced skipping: Agent cannot skip steps (enforced sequence)
• Better focus: Agent only considers current step’s requirements
• Verbatim text: Actions can deliver exact text without agent paraphrasing

​

2. Cost Reduction

• Smaller context: Each step has minimal instructions (not thousands of characters)
• Efficient models: GPT-4o-mini often sufficient where GPT-4o or GPT-4.1 was previously required
• Reduced tokens: Less redundant information passed to the model

​

3. Maintainability

• Isolated changes: Modify step instructions without side effects
• Easy reordering: Change workflow sequence without rewriting everything
• Clear structure: Self-documenting workflow stages

​

4. Testability

• Step-by-step verification: Confirm each stage works correctly
• State inspection: Check data collection at each point
• Reproducible scenarios: Easy to recreate specific workflow states

​

Real-World Example

​

Before: Monolithic Prompt (Simplified)

You are a contact form agent. Follow these steps:

1. Greet the user warmly
2. Collect their name
3. Collect their email (must contain @ and .)
4. Ask for preferred contact time (morning, afternoon, or evening)
5. If they prefer morning/afternoon, schedule a phone call
6. If they prefer evening, schedule an email follow-up
7. Confirm all information
8. Thank them and end the conversation

Remember to:
- Be polite and professional
- Validate email format before proceeding
- Always confirm information before moving on
[... 50+ more instructions ...]

• Agent sometimes skips validation
• All 50+ instructions visible at once
• Expensive to run (requires GPT-4)
• Hard to maintain

​

After: Step Workflows

Step 1: GREET
  Goal: Welcome the user
  Instructions: "Greet the user warmly and explain you'll help them with their contact request."

Step 2: COLLECT_NAME
  Goal: Collect user's name
  Inputs: {name: string (required)}

Step 3: COLLECT_EMAIL
  Goal: Collect user's email
  Inputs: {email: string (required)}
  Validation: Must contain @ and .

Step 4: COLLECT_TIME
  Goal: Ask for preferred contact time
  Inputs: {time: enum[morning, afternoon, evening] (required)}

Step 5A: SCHEDULE_PHONE
  (if time is morning/afternoon)

Step 5B: SCHEDULE_EMAIL
  (if time is evening)

Step 6: CONFIRM
  Goal: Confirm all information

Step 7: CLOSE
  Goal: Thank and end
  (terminal step)

• Agent sees only current step
• Validation automatically enforced
• Works with GPT-4o-mini (90% cost reduction compared to GPT-4o)
• Easy to add/remove/modify steps

​

Getting Started

1. Creating a simple “Hello World” workflow
2. Collecting user inputs with validation
3. Building multi-step workflows with data persistence
4. Adding lifecycle actions for polished experiences
5. Implementing conditional branching logic
6. Handling validation errors and retries
7. Integrating with external tools and systems

​

Reference