Add Structured Steps to an Agent

Add a FLOW section to a hotel booking agent, giving it structured steps that guide users through a reservation process. By the end, you know how to:

Define a flow with named steps and transitions
Use GATHER to collect information from users
Add conditional branching with ON_INPUT and ON_RESULT
Handle tool call results within flow steps
Implement validation and correction patterns

Prerequisites

Completed Build your first agent
A project open in Studio
Understanding of agent and tool definitions

What You’ll Build

A hotel booking agent with a FLOW section that walks users through structured steps: entering a destination, selecting dates, searching for hotels, choosing a room, entering guest details, and confirming the booking. Each step collects specific information before moving forward. The agent is the same kind of agent you built in the first tutorial — you are simply adding structured steps via a FLOW block.

Step 1: Create the agent with tools

Create hotel_booking.agent.abl and start with the agent definition and tools:

AGENT: Hotel_Booking
GOAL: "Guide users through a complete hotel booking process step by step"

PERSONA: |
  Professional and friendly hotel booking assistant.
  Guides users through each step clearly.
  Confirms information at each stage.

TOOLS:
  search_hotels(destination: string, checkin: date, checkout: date, guests: number) -> {hotels: array}
    description: "Search for available hotels"

  create_booking(hotel_id: string, guest_name: string, email: string, phone: string) -> {booking_id: string, confirmation: string}
    description: "Create a hotel booking"

Step 2: Add a FLOW section

Add the FLOW block to give the agent structured steps. Any agent can include a FLOW section — it does not change the type of agent, it just adds a step-by-step structure to the conversation:

FLOW:
  steps:
    - welcome
    - get_destination
    - get_dates
    - get_guests
    - search_and_show
    - select_hotel
    - get_guest_details
    - confirm_booking

The steps list declares the order of steps. Each step name maps to a definition below. The first step in the list is the default entry point.

Step 3: Add the welcome step

  welcome:
    REASONING: false
    RESPOND: |
      Welcome to Hotel Booking!

      I'll help you find and book the perfect hotel.
      Let's get started with your destination.
    THEN: get_destination

Within a flow, each step can set REASONING: false to follow exact rules without LLM reasoning, or REASONING: true to use the LLM for that step. Since agents reason by default, REASONING: true is the default for flow steps — you only need to set REASONING: false explicitly when you want deterministic, non-LLM behavior. The RESPOND block sends a message to the user. THEN transitions to the next step.

Step 4: Collect information with GATHER

Add the destination, dates, and guest count steps:

  get_destination:
    REASONING: false
    GATHER:
      - destination: required
        prompt: "Where would you like to stay?"
    THEN: get_dates

  get_dates:
    REASONING: false
    GATHER:
      - checkin_date: required
        type: date
        prompt: "What is your check-in date?"
      - checkout_date: required
        type: date
        prompt: "What is your check-out date?"
    THEN: get_guests

  get_guests:
    REASONING: false
    GATHER:
      - num_guests: required
        type: number
        prompt: "How many guests?"
    THEN: search_and_show

GATHER collects one or more pieces of information from the user. Each field specifies:

name — The variable name to store the value
required — Whether the field must be provided
type — The expected data type (string, number, date, email, phone)
prompt — The question shown to the user

When a step has multiple GATHER fields, the Runtime collects them in a natural conversational flow. Users can provide multiple values in a single message.

Step 5: Call a tool and handle results

Add the hotel search step with result handling:

  search_and_show:
    REASONING: false
    CALL: search_hotels(destination, checkin_date, checkout_date, num_guests)
    ON_SUCCESS:
      RESPOND: |
        I found these hotels in {{destination}}:

        {{#each hotels}}
        {{add @index 1}}. {{name}} - ${{price}}/night ({{rating}} stars)
        {{/each}}

        Which hotel would you like to book? Enter the number.
      THEN: select_hotel
    ON_FAIL:
      RESPOND: "No hotels found for your criteria. Let's try different dates."
      THEN: get_dates

The CALL keyword executes a tool with session variables as arguments. ON_SUCCESS runs when the tool returns data, and ON_FAIL runs when it fails. The response template uses Handlebars syntax ({{#each}}, {{name}}) to render dynamic data.

Step 6: Add conditional branching with ON_INPUT

Add the hotel selection step with input validation:

  select_hotel:
    REASONING: false
    GATHER:
      - hotel_selection: required
    ON_INPUT:
      - IF: input is_number AND input >= 1 AND input <= hotels.length
        SET: selected_hotel = hotels[input - 1]
        THEN: get_guest_details
      - ELSE:
        RESPOND: "Please enter a valid hotel number."
        THEN: select_hotel

ON_INPUT provides conditional branching based on what the user enters. Each branch has:

IF — A condition to evaluate against the input
SET — Variable assignments (optional)
RESPOND — A message to send (optional)
THEN — The next step to transition to

The ELSE branch catches any input that does not match the preceding conditions.

Step 7: Collect guest details

  get_guest_details:
    REASONING: false
    GATHER:
      - guest_name: required
        prompt: "What is the primary guest name (as on ID)?"
      - guest_email: required
        type: email
        prompt: "What is your email address?"
      - guest_phone: required
        prompt: "What is your phone number?"
    THEN: confirm_booking

The type: email declaration tells the Runtime to validate the input as an email address. If the user provides an invalid format, the Runtime re-prompts automatically.

Step 8: Confirm and complete the booking

  confirm_booking:
    REASONING: false
    RESPOND: |
      Please review your booking:

      Hotel: {{selected_hotel.name}}
      Dates: {{checkin_date}} to {{checkout_date}}
      Guests: {{num_guests}}
      Guest: {{guest_name}} ({{guest_email}})

      Type "confirm" to complete or "change" to start over.
    ON_INPUT:
      - IF: input == "confirm" OR input == "yes"
        CALL: create_booking(selected_hotel.id, guest_name, guest_email, guest_phone)
        ON_SUCCESS:
          RESPOND: |
            Booking confirmed!

            Confirmation: {{booking_id}}
            Hotel: {{selected_hotel.name}}
            Check-in: {{checkin_date}}
            Check-out: {{checkout_date}}
            Guest: {{guest_name}}

            A confirmation email has been sent to {{guest_email}}.
          THEN: COMPLETE
        ON_FAIL:
          RESPOND: "Booking failed. Please try again."
          THEN: confirm_booking
      - IF: input == "change"
        THEN: get_destination
      - ELSE:
        RESPOND: "Please type 'confirm' or 'change'."
        THEN: confirm_booking

Nested CALL inside ON_INPUT executes the tool only when the user confirms. The special step name COMPLETE ends the session. Failed bookings loop back to the confirmation step.

Step 9: Add the completion condition

COMPLETE:
  - WHEN: booking_confirmed == true
    RESPOND: "Your booking is complete. Thank you!"

Step 10: Test the full flow

Open the Chat panel and walk through the booking:

The agent greets you and asks for a destination
Enter “Paris” — the agent asks for dates
Enter check-in and check-out dates — the agent asks for guest count
Enter “2” — the agent searches for hotels and shows results
Enter a hotel number — the agent asks for guest details
Provide name, email, and phone — the agent shows a summary
Type “confirm” — the booking completes

Open the Traces panel to see each step as a separate trace span. The flow transitions appear as arrows between steps.

Full Agent Definition

AGENT: Hotel_Booking
GOAL: "Guide users through a complete hotel booking process step by step"

PERSONA: |
  Professional and friendly hotel booking assistant.
  Guides users through each step clearly.
  Confirms information at each stage.

TOOLS:
  search_hotels(destination: string, checkin: date, checkout: date, guests: number) -> {hotels: array}
    description: "Search for available hotels"

  create_booking(hotel_id: string, guest_name: string, email: string, phone: string) -> {booking_id: string, confirmation: string}
    description: "Create a hotel booking"

FLOW:
  steps:
    - welcome
    - get_destination
    - get_dates
    - get_guests
    - search_and_show
    - select_hotel
    - get_guest_details
    - confirm_booking

  welcome:
    REASONING: false
    RESPOND: |
      Welcome to Hotel Booking!

      I'll help you find and book the perfect hotel.
      Let's get started with your destination.
    THEN: get_destination

  get_destination:
    REASONING: false
    GATHER:
      - destination: required
        prompt: "Where would you like to stay?"
    THEN: get_dates

  get_dates:
    REASONING: false
    GATHER:
      - checkin_date: required
        type: date
        prompt: "What is your check-in date?"
      - checkout_date: required
        type: date
        prompt: "What is your check-out date?"
    THEN: get_guests

  get_guests:
    REASONING: false
    GATHER:
      - num_guests: required
        type: number
        prompt: "How many guests?"
    THEN: search_and_show

  search_and_show:
    REASONING: false
    CALL: search_hotels(destination, checkin_date, checkout_date, num_guests)
    ON_SUCCESS:
      RESPOND: |
        I found these hotels in {{destination}}:

        {{#each hotels}}
        {{add @index 1}}. {{name}} - ${{price}}/night ({{rating}} stars)
        {{/each}}

        Which hotel would you like to book? Enter the number.
      THEN: select_hotel
    ON_FAIL:
      RESPOND: "No hotels found for your criteria. Let's try different dates."
      THEN: get_dates

  select_hotel:
    REASONING: false
    GATHER:
      - hotel_selection: required
    ON_INPUT:
      - IF: input is_number AND input >= 1 AND input <= hotels.length
        SET: selected_hotel = hotels[input - 1]
        THEN: get_guest_details
      - ELSE:
        RESPOND: "Please enter a valid hotel number."
        THEN: select_hotel

  get_guest_details:
    REASONING: false
    GATHER:
      - guest_name: required
        prompt: "What is the primary guest name (as on ID)?"
      - guest_email: required
        type: email
        prompt: "What is your email address?"
      - guest_phone: required
        prompt: "What is your phone number?"
    THEN: confirm_booking

  confirm_booking:
    REASONING: false
    RESPOND: |
      Please review your booking:

      Hotel: {{selected_hotel.name}}
      Dates: {{checkin_date}} to {{checkout_date}}
      Guests: {{num_guests}}
      Guest: {{guest_name}} ({{guest_email}})

      Type "confirm" to complete or "change" to start over.
    ON_INPUT:
      - IF: input == "confirm" OR input == "yes"
        CALL: create_booking(selected_hotel.id, guest_name, guest_email, guest_phone)
        ON_SUCCESS:
          RESPOND: |
            Booking confirmed!

            Confirmation: {{booking_id}}
            Hotel: {{selected_hotel.name}}
            Check-in: {{checkin_date}}
            Check-out: {{checkout_date}}
            Guest: {{guest_name}}

            A confirmation email has been sent to {{guest_email}}.
          THEN: COMPLETE
        ON_FAIL:
          RESPOND: "Booking failed. Please try again."
          THEN: confirm_booking
      - IF: input == "change"
        THEN: get_destination
      - ELSE:
        RESPOND: "Please type 'confirm' or 'change'."
        THEN: confirm_booking

COMPLETE:
  - WHEN: booking_confirmed == true
    RESPOND: "Your booking is complete. Thank you!"

What You Learned

The FLOW block adds structured steps to any agent for step-by-step conversations
GATHER collects typed information from users with prompts and validation
REASONING: false makes a step follow exact rules without LLM reasoning; REASONING: true (the default) uses the LLM
CALL executes tools with session variables as arguments
ON_SUCCESS and ON_FAIL handle tool results
ON_INPUT provides conditional branching based on user input
SET assigns values to session variables
THEN transitions to the next step; THEN: COMPLETE ends the session
Handlebars templates ({{variable}}, {{#each}}) render dynamic data in responses

Next Steps

Multi-agent and knowledge — Create a supervisor that routes between specialist agents and add a knowledge base.
Safety, testing, and publishing — Add guardrails, run evaluations, and publish your agent.

When building flows, use REASONING: true on steps where you want the LLM to handle edge cases naturally. Reserve REASONING: false for deterministic validation and branching logic.

Building Agents

Administration

Add Structured Steps to an Agent

Prerequisites

What You’ll Build

Step 1: Create the agent with tools

Step 2: Add a FLOW section

Step 3: Add the welcome step

Step 4: Collect information with GATHER

Step 5: Call a tool and handle results

Step 6: Add conditional branching with ON_INPUT

Step 7: Collect guest details

Step 8: Confirm and complete the booking

Step 9: Add the completion condition

Step 10: Test the full flow

Full Agent Definition

What You Learned

Next Steps

Building Agents

Administration

Documentation Index

​Prerequisites

​What You’ll Build

​Step 1: Create the agent with tools

​Step 2: Add a FLOW section

​Step 3: Add the welcome step

​Step 4: Collect information with GATHER

​Step 5: Call a tool and handle results

​Step 6: Add conditional branching with ON_INPUT

​Step 7: Collect guest details

​Step 8: Confirm and complete the booking

​Step 9: Add the completion condition

​Step 10: Test the full flow

​Full Agent Definition

​What You Learned

​Next Steps

Prerequisites

What You’ll Build

Step 1: Create the agent with tools

Step 2: Add a FLOW section

Step 3: Add the welcome step

Step 4: Collect information with GATHER

Step 5: Call a tool and handle results

Step 6: Add conditional branching with ON_INPUT

Step 7: Collect guest details

Step 8: Confirm and complete the booking

Step 9: Add the completion condition

Step 10: Test the full flow

Full Agent Definition

What You Learned

Next Steps