Quick Start Guide

Welcome to Bivariant! This guide will get you up and running with your first AI application in just 15 minutes. You'll create a functional customer support chatbot that demonstrates the platform's core capabilities.

Prerequisites

Before we begin, ensure you have:

• A Bivariant account (sign up at bivariant.com)
• Basic familiarity with web applications
• 15 minutes of focused time

No coding experience is required – we'll use Bivariant's visual development tools throughout this tutorial.

Step 1: Access Your Organization

After signing in, you'll land on your organization dashboard. Every Bivariant account starts with:

• Organization: Your top-level workspace (e.g., "Acme Corp")
• Default Space: An isolated environment for your projects
• Admin Account: Your personal account with full permissions

Take a moment to explore the interface. The left sidebar contains navigation to all platform features: Apps, Blueprints, Collections, and more.

Step 2: Install Your First App

We'll start by installing a pre-built customer support app from the marketplace.

1. Navigate to Apps: Click "Apps" in the left sidebar
2. Access Marketplace: Click "Browse Marketplace" in the top-right corner
3. Find Support App: Search for "Customer Support Assistant"
4. Install App: Click "Install" and confirm the installation

The installation process creates:

• A customer support agent with pre-configured conversation skills
• A help center with sample articles
• Integration templates for common support tools
• A web widget for embedding on your website

Installation typically takes 30-60 seconds as Bivariant provisions the necessary resources and configurations.

Step 3: Configure Your Support Agent

Once installed, let's customize the support agent:

1. Open App Settings: Click on your newly installed "Customer Support Assistant" app
2. Access Agents: Navigate to the "Agents" tab
3. Select Support Agent: Click on "Support Agent" from the list

You'll see the agent configuration interface with several key sections:

Basic Information

• Name: Change from "Support Agent" to "Your Company Assistant"
• Description: Add your company-specific context
• Avatar: Upload your company logo or choose from provided options

Conversation Settings

Configure how your agent responds:

• Greeting Message: Customize the initial message users see
• Tone: Choose from Professional, Friendly, or Custom
• Response Length: Set preference for brief or detailed responses
• Escalation Rules: Define when to transfer to human agents

Knowledge Base

Connect your agent to information sources:

1. Click "Add Knowledge Source"
2. Select "Help Center Articles" (pre-loaded with examples)
3. Optionally add your existing documentation or FAQ

Save your changes – the agent will automatically update across all channels.

Step 4: Create a Simple Flow

Now let's create a basic workflow that handles common support requests:

1. Navigate to Flows: Click "Flows" in the left sidebar
2. Create New Flow: Click "Create Flow"
3. Choose Template: Select "Basic Support Workflow"
4. Name Your Flow: Enter "Customer Inquiry Handler"

The visual flow builder opens with a pre-built template containing:

Flow Components

• Trigger: When a new conversation starts
• Intent Detection: Classify user inquiries (billing, technical, general)
• Route Logic: Direct conversations based on intent
• Agent Response: Generate contextual responses
• Escalation: Transfer complex issues to human agents

Customization

Modify the flow for your needs:

1. Click Intent Detection node: Add your specific inquiry types
2. Modify Route Logic: Adjust decision criteria
3. Update Responses: Customize agent responses per intent type
4. Test Flow: Use the built-in simulator to verify behavior

Save and Activate the flow to make it live.

Step 5: Test Your Application

Time to see your creation in action:

Built-in Chat Interface

1. Navigate to Apps: Return to your apps list
2. Open App: Click on "Customer Support Assistant"
3. Test Chat: Click "Test Conversation" in the top-right
4. Start Conversation: Send a message like "I need help with billing"

Watch as your agent:

• Detects the billing intent
• Routes through your custom flow
• Provides contextual responses
• Offers relevant help articles

Web Widget Testing

For a real-world experience:

1. Get Embed Code: Navigate to "Channels" → "Web Widget"
2. Copy Code: Copy the provided JavaScript snippet
3. Test Page: Use the built-in preview or add to your website

The widget appears as a chat bubble that visitors can click to start conversations with your AI agent.

Step 6: Monitor and Improve

Your application is now live! Here's how to monitor and improve performance:

Analytics Dashboard

Access real-time insights:

• Conversation Volume: Track daily interaction counts
• Resolution Rate: See how often the agent resolves issues without escalation
• Response Time: Monitor agent performance metrics
• Popular Topics: Identify common customer inquiries

Continuous Improvement

Use analytics to enhance your application:

1. Review Unresolved Conversations: Identify gaps in knowledge or flow logic
2. Update Knowledge Base: Add new articles based on frequent questions
3. Refine Flows: Adjust routing logic for better intent detection
4. Train Agent: Provide feedback on responses to improve accuracy

What You've Accomplished

Congratulations! In just 15 minutes, you've:

✅ Installed a production-ready AI application
✅ Configured an intelligent customer support agent
✅ Created a custom workflow for handling inquiries
✅ Tested real conversations with your AI assistant
✅ Deployed a web widget for customer interactions

Your customer support system is now capable of:

• 24/7 Availability: Handle customer inquiries around the clock
• Intelligent Routing: Automatically categorize and route inquiries
• Contextual Responses: Provide relevant answers based on your knowledge base
• Seamless Escalation: Transfer complex issues to human agents when needed
• Performance Tracking: Monitor effectiveness and identify improvement opportunities

Next Steps

Ready to go deeper? Here are your recommended next steps:

Immediate Enhancements

• Customize Your Brand: Update colors, logos, and messaging
• Add More Channels: Enable email, SMS, or social media support
• Import Your Data: Connect existing customer databases

Advanced Features

• Build Custom Integrations: Connect to your CRM, helpdesk, or billing systems
• Create Complex Flows: Build sophisticated automation workflows
• Develop Custom Blueprints: Package your solutions for reuse

Enterprise Deployment

• User Management: Add team members and configure permissions
• Production Deployment: Scale for production workloads
• Security Configuration: Implement enterprise security policies

Getting Help

Need assistance? Here are your resources:

• Community Forum: Connect with other developers
• Documentation: Comprehensive guides and references
• Support Center: Direct help from our team
• Video Tutorials: Step-by-step visual guides

Welcome to the future of AI application development. You're now ready to build sophisticated AI solutions that deliver real business value!