Before You Begin
Ensure your chatbot meets these requirements:- HTTPS Endpoint — Accessible via a secure HTTPS URL
- OpenAI Chat Format — Accepts and returns messages in OpenAI’s chat completion format
- Authentication — Have your API key or token ready along with any required headers
What You’ll Need
- Chatbot endpoint URL (e.g.,
https://your-chatbot.com/api/chat) - Authentication credentials and any required headers
- Chatbot name and description
Chatbot Configuration
Chatbot Name Guidelines
- Use clear, descriptive names (15-50 characters)
- Avoid technical jargon
- Examples: “Customer Support Assistant”, “Code Review Bot”, “Sales Qualifier”
Chatbot Description
Your description helps Botster understand:- What your chatbot does
- When to use it
- What to expect
“Helps customers troubleshoot technical issues with our software. Can diagnose problems, suggest solutions, and escalate complex cases to human support.”For detailed guidance, see Write Effective Descriptions.
System Prompt (Optional)
Use the same base system prompt your model uses in production. Botster forwards it as-is with every simulation request.- Leave blank if your model injects its own prompt
- Keep it concise—Botster adds the scenario-specific simulation prompt separately
- Update when your production prompt changes
Setup Steps
- Navigate to Chatbots → Add Chatbot
- Enter your chatbot name
- Write a clear description of what your chatbot does
- Provide your endpoint URL
- Add authentication headers (API key, Bearer token, or custom headers)
- (Optional) Add your system prompt
- Click Test Connection to verify
- Save your chatbot
Authentication Options
Botster supports several authentication methods: API Key HeaderSuccess Indicators
- Green connection status on the Chatbot page
- Test message returns expected response
Troubleshooting
Connection Timeout
- Verify your endpoint URL is correct
- Check server accessibility
- Ensure firewalls allow Botster’s IP addresses
Authentication Failed
- Verify your API key or token
- Check header format matches your API requirements
Invalid Response Format
- Verify your API returns messages in OpenAI chat completion format
- Ensure your API returns valid JSON
Next Steps
- Write Effective Descriptions — Improve simulation quality
- Define Simulation Prompts — Target specific scenarios
- Quickstart — Run your first simulation