Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.boostgpt.co/llms.txt

Use this file to discover all available pages before exploring further.

Widget Setup

Greeting messages appear above the bubble before the user opens the chat. Make them:
  • Specific: “Questions about our pricing plans?” beats “Need help?”
  • Action-oriented: Tell users what you can help with
  • Brief: 1-2 sentences max per greeting card
  • Varied: Use 2-3 different greetings to avoid repetition
Configure greetings in Branding → Content → Message Greetings.
Auto-open shows the chat frame automatically after a delay:
  • Don’t auto-open on landing pages — let users explore first
  • Auto-open on support/help pages — users are already looking for help
  • 5-10 seconds is a good default delay
  • Disable for mobile — screen space is limited, let users choose to open
If your site has authentication, use SSO to identify users:
  • Agent can greet them by name
  • Conversation history persists across sessions
  • Support team sees who they’re talking to
  • See SSO setup guide for implementation
The widget inherits your agent’s branding:
  • Accent color: Set in Branding → Design. Use your primary brand color.
  • Avatar: Upload a recognizable icon or team photo
  • Bubble icon: Choose from 16 icons or use your avatar
  • Position: Bottom-right works for most sites. Use bottom-left if you have a conflicting element.

Trigger Timing

Give users time to orient themselves before offering help.Recommended delays:
  • Simple pages: 30-45 seconds
  • Complex forms: 45-90 seconds
  • Technical setup: 90-180 seconds
Distinguish between:
  • User reading carefully (good)
  • User stuck and frustrated (needs help)
Use multiple signals: time + inactivity + scroll position.
Exit intent (mouse leaving window) is powerful but can feel aggressive. Reserve for high-value pages like checkout.

Trigger Frequency

  • Max 2-3 triggers per session
  • Never more than 1 at a time
  • Wait 5+ minutes between triggers
If a user dismisses a trigger:
  • Don’t show the same trigger again that session
  • Consider a 24-hour cooldown for that event
  • Track dismissal patterns to improve targeting
Users who see too many triggers become blind to them. Quality over quantity - fewer, better-timed triggers perform better.

Messaging

❌ “Need help?” ✅ “Having trouble with payment? I can help!”❌ “Click here for support” ✅ “Stuck on this step? I can walk you through it.”
If your brand is:
  • Professional: “Need assistance with checkout?”
  • Friendly: “Hey! Can I help with that?”
  • Technical: “Encountering an issue? Let’s debug together.”
✅ “Your cart is saved for 30 minutes” ❌ “Buy now or lose your cart!”✅ “Questions before you go?” ❌ “Don’t leave! We need you!”

Context

The more context your agent has, the better it can help:
// Good
boostgpt.trigger('checkout_help', {
  cart_value: '$149',
  items: 3,
  user_name: 'Sarah',
  time_on_page: 45,
  current_step: 'payment'
});

// Not as helpful
boostgpt.trigger('help', {});
boostgpt.trigger('help_needed', { page: '/settings' }, {
  text: 'Need help with settings?',
  user: {
    id: 'user_123',
    name: 'Sarah Chen',
    email: 'sarah@example.com',
    plan: 'pro'
  }
});
This enables personalized responses.
Include:
  • Current page/step
  • Previous pages visited
  • Actions already taken
  • Time spent

Trigger Style

Triggers appear as toast-style message cards stacked above the chat widget bubble. They feel personal and conversational — clicking opens the chat with context.
SituationExample Text
Checkout help”Having trouble checking out? I can help!”
Onboarding stuck”Stuck on this step? Let me walk you through it.”
Error recovery”Something went wrong. Click here for help.”
Feature discovery”Did you know you can automate this?”

Training Your Agent

Your agent should know:
  • Product features and pricing
  • Common issues and solutions
  • Policies (shipping, returns, refunds)
  • Technical documentation
Templates should:
  • Describe the situation clearly
  • Include all relevant context
  • Provide instructions on how to help
  • Set the right tone
Before deploying, test:
  • Common user questions
  • Edge cases
  • Error scenarios
  • Various context combinations

Analytics & Optimization

MetricWhat It Tells You
Widget OpensHow often users engage with the chat
Trigger View RateHow often users see trigger cards
Trigger Click RateHow often users click trigger cards
Resolution RateHow often chat resolves the issue
Conversion LiftImpact on desired outcomes
Test variations of:
  • Trigger message text
  • Trigger timing and delay
  • Greeting messages
  • Auto-open vs manual open
  • High view, low click: Message isn’t compelling
  • High click, low resolution: Agent needs better training
  • Low view: Trigger timing/conditions need adjustment

Common Mistakes

Don’t do these:
  1. Triggering on page load - Let users settle first
  2. Too many triggers - Causes fatigue and annoyance
  3. Generic messages - “Need help?” is forgettable
  4. Blocking the page - Never prevent users from continuing
  5. No dismiss option - Always let users close triggers
  6. Same trigger repeatedly - Respect when users say no
  7. Ignoring mobile - Test on all devices
  8. No analytics - You can’t improve what you don’t measure

Checklist

Before launching, verify: Widget:
  • Accent color matches your brand
  • Greeting messages are specific and helpful
  • Auto-open timing is appropriate (or disabled)
  • SSO configured for authenticated users
  • Works on mobile devices
  • Position doesn’t conflict with other page elements
Triggers:
  • Timing feels natural, not aggressive
  • Trigger messages are specific and helpful
  • Agent is trained on relevant content
  • Dismissals are respected
  • Rate limits won’t be exceeded
  • Legal/privacy requirements are met

Next Steps

Quickstart

Set up your first widget and trigger

Use Case Guides

Real-world implementations