Expertise AI Knowledge Base

Core Concepts & Structure

Understanding playbook anatomy, steps, branching, and rules

Last updated on October 27, 2025

Core Concepts & Structure

Playbook Anatomy

Every playbook consists of five key components:

1. Steps (Numbered Instructions)

Steps are the building blocks of your playbook. Each step is numbered and describes what happens at that point in the conversation:
1. @ask_question: "What is your name?" 2. @ask_question: "What is your email address?"
Steps execute sequentially by default unless you add branching logic.

2. Tools (Actions the Agent Takes)

Tools are actions prefixed with @ that tell the agent what to do. Examples:
Multiple tools can be combined in a single step (with some exceptions). See all tools in
Getting Started with Playbooks
.

3. Triggers (Activation Conditions)

The trigger defines when your playbook activates:
  • Specific phrase: "I want to book a demo" or "Contact sales"
  • Always active: Leave blank to make the playbook available anytime
  • URL targeting: Use conversation starters to trigger on specific pages

4. Rules (Optional Domain Guidance)

The RULES section provides domain-specific guidance to the agent during playbook execution:
RULES: - Mention our 30-day free trial when speaking to SMBs - Emphasize 24/7 support availability for Enterprise customers
Important: RULES are optional and should be minimal (0-3 rules). They appear AFTER all steps including @stop_playbook.

5. Branching Logic

Branching lets you create different paths based on user responses:
1. @ask_question: "What's your company size?" @show_options["1-50", "51-200", "201+"] - If the answer is "1-50", proceed to Step 2. - If the answer is "51-200", proceed to Step 3. - If the answer is "201+", proceed to Step 4.

Structural Rules

How Steps Work

Sequential by Default: Without branching logic, steps proceed to the next number automatically:
1. @ask_question: "What is your name?" 2. @ask_question: "What is your email?" 3. @stop_playbook
One Action at a Time: Each step should focus on a single conversational moment.
Turn-Taking: After each step, the user gets a chance to respond before the next step executes.

When to Add Branching Bullets

Add branching bullets when different options lead to different steps:
1. @ask_question: "Budget allocated?" @show_options["Yes", "No"] - If the answer is "Yes", proceed to Step 2. - If the answer is "No", proceed to Step 5.
Omit branching bullets when all options proceed to the same next step:
1. @ask_question: "Which area?" @show_options["Billing", "Technical", "Account"] 2. @ask_question: "What is your email?"

The Role of @stop_playbook

Tool: @stop_playbook
ends playbook execution and returns the agent to general conversation mode.
Critical: Every path through your playbook must reach @stop_playbook eventually.

Combination Constraints

Must Be Alone:
Can Combine Freely:
  • All other tools can be combined as needed

Language Handling

  • Tool tags: Must always be in English (@ask_question, @show_options, etc.)
  • Playbook content: Can be written in any language
  • Agent responses: Automatically translated to the visitor's detected language

Branching Logic Deep Dive

Rule 1: Different Options → Different Steps = Add Branches

1. @ask_question: "Company size?" @show_options["Small", "Medium", "Large"] - If "Small", proceed to Step 2. - If "Medium", proceed to Step 3. - If "Large", proceed to Step 4.

Rule 2: All Options → Same Step = Omit Branches

1. @ask_question: "Which product?" @show_options["Product A", "Product B", "Product C"] 2. @ask_question: "What is your email?"
All three products lead to Step 2, so no branching bullets are needed.

Examples: Proper vs Improper Branching

Improper (Unnecessary):
2. @ask_question: "Which department?" @show_options["Sales", "Support", "Billing"] - If "Sales", proceed to Step 3. - If "Support", proceed to Step 3. - If "Billing", proceed to Step 3.
Proper:
2. @ask_question: "Which department?" @show_options["Sales", "Support", "Billing"] 3. @ask_question: "What is your email?"

Learn More