Skip to main content

​
Quickstart Guide

Get your AI customer support assistant up and running in under 10 minutes. This guide walks you through creating your first project, connecting knowledge sources, and deploying your AI.

​
Prerequisites

Before you begin, you’ll need:
  • A botBrains account (sign up if you haven’t already)
  • Access to your knowledge sources (documentation, help articles, or FAQ pages)
  • A deployment target (your website, Zendesk, or Salesforce)

​
Step 1: Create Your First Project

  1. Log in to the botBrains platform
  2. Click Create Project on the projects page
  3. Enter a name for your project (e.g., “Customer Support Bot”)
  4. Click Create
Your project is now created. Think of a project as a workspace for on AI agent - you can create multiple projects for different use cases or departments.

​
Step 2: Add Your Knowledge

Your AI needs knowledge to answer customer questions. Let’s connect your first knowledge source.

​
Connect a Documentation Site

  1. Navigate to Data Providers in the sidebar
  2. Click Add Data Provider
  3. Choose Website as the provider type
  4. Enter your documentation URL (e.g., https://docs.yourcompany.com)
  5. Configure crawling options:
    • Max Pages: How many pages to crawl (start with 100)
    • Crawl Frequency: How often to refresh (daily recommended)
  6. Click Create and Sync
botBrains will now crawl your documentation and extract knowledge. This typically takes a few minutes depending on the number of pages.
Start Small: Begin with your most important documentation pages. You can always add more knowledge sources later.

​
Alternative: Add Knowledge Manually

If you don’t have a documentation site yet, you can add knowledge manually:
  1. Go to Data Providers > Snippets
  2. Click Add Snippet
  3. Enter a title and paste your content
  4. Add relevant tags for better retrieval
  5. Click Save

​
Step 3: Configure AI Behavior

Tell your AI how to communicate with customers.
  1. Navigate to Behavior in the sidebar
  2. You’ll see a default profile - click Edit
  3. Configure the basic settings:
    • Name: Give your AI a name (e.g., “Alex”)
    • Tone: Define communication style (professional, friendly, technical)
    • Instructions: Provide guidelines for responses
Example instructions: 
You are a helpful customer support assistant for Acme Corp.
- Always be friendly and professional
- Keep responses concise and actionable
- If you don't know something, admit it and offer to escalate
- Include links to relevant documentation when possible
  1. Click Save
Profiles control how your AI behaves. You can create multiple profiles for different audiences or use cases.

​
Step 4: Test Your AI

Before deploying to customers, test your AI’s responses directly in the Behavior configuration.
  1. While still in the Behavior tab (from Step 3), look at the preview panel on the right side
  2. The preview updates in real-time as you configure your AI’s behavior
  3. Type questions that customers might ask in the test chat
  4. Review the responses:
    • Are they accurate?
    • Do they cite the right sources?
    • Is the tone appropriate?
  5. Make adjustments to your instructions on the left and see changes instantly
The preview panel uses your actual knowledge sources and settings, so you’re testing exactly how your AI will respond to customers.
If responses need improvement:
  • Add more specific knowledge to your data providers
  • Refine your profile instructions in the Behavior tab
  • Test with different example questions to ensure consistency

​
Step 5: Deploy Your AI

Now deploy your AI to start helping customers. Choose the integration that matches your workflow:

Website Integration

Add a chat widget to your website with customizable styling.

Zendesk Integration

Automate ticket responses and field predictions in Zendesk.

Salesforce Integration

Handle cases in Salesforce Service Cloud with AI assistance.

Slack Integration

Bring AI support directly into your team’s Slack workspace.

​
Step 6: Monitor and Improve

After deployment, continuously improve your AI:
  1. Review Conversations: Go to Conversations to see how your AI is performing
  2. Check Topics: Visit Topics to understand what customers are asking about
  3. Analyze Metrics: Review Metrics for performance data
  4. Add Knowledge: When you spot gaps, add more knowledge sources or snippets
  5. Refine Behavior: Update your profile instructions based on real interactions
Iterate Quickly: Start with basic setup and improve based on real customer interactions. Perfect is the enemy of good!

​
Common Next Steps

Once you’re up and running:

​
Getting Help

Need assistance? Here are your resources:
  • Documentation: Browse our comprehensive docs
  • Support: Email support@botbrains.io
  • Platform: Use the in-app chat for quick questions

​
What You’ve Accomplished

You’ve successfully:
  • ✅ Created your first botBrains project
  • ✅ Connected knowledge sources
  • ✅ Configured AI behavior
  • ✅ Tested responses
  • ✅ Deployed your AI to customers
  • ✅ Set up monitoring
Your AI is now helping customers 24/7. Welcome to automated customer support!