AI Bots Console
Settings
Properly configuring your bot is essential for accuracy, performance, and reliability. The Settings section lets you manage prompts, models, query behavior, and search precision.
Let’s now look at how to explore and apply these predefined prompts.
Add up to 4 questions relevant to your bot:
To preview how your saved starter questions look in your console and user experience:
Then, test the parameter live in the Playground UI:
Settings Navigation
Bot Settings: Part 1
Set Chat & Embedding Models
Bot Settings: Part 2
Prompt Types & Prompt Library
Bot Settings: Part 3
Adjust Bot Temperature
Starter Questions
Define Starter Prompts
Query Parameters
Pass Contextual Inputs to Bot
Semantic Similarity Score
Fine-Tune Result Relevance
Bot Settings: Part 1
Configure the base models for your bot.- Navigate to Bot Settings
- Update the Bot name (if needed)
- Choose your Chat model
- Select an Embedding model
- Save the settings
Bot Settings: General Configuration
Bot Settings: Part 2 – Prompts & Library
✅ Configure Prompt Behavior
- Prompt for Own Data: Bot only responds using provided data. No hallucinations — replies with “I don’t know” if unsure.
- Prompt for Web Data: Good for standalone, follow-up questions without context.
- Prompt Library: Use system-defined prompts for use cases like Interviewer, Educator, or Assistant.
Prompt Configuration Panel in Bot Settings
Using the Prompt Library
1
Browse and Apply Predefined Prompts
Click Prompt lib to access the built-in library of system prompts.
Select a category that matches your bot’s purpose — e.g., Position Interviewer, Storyteller, FAQ Agent.
Select a category that matches your bot’s purpose — e.g., Position Interviewer, Storyteller, FAQ Agent.
Prompt Library: Browse Built-in Prompt Options
2
Preview and Confirm Selection
After selecting a prompt, preview its description and sample usage.
Click Use Prompt to confirm and apply it to your bot.
Click Use Prompt to confirm and apply it to your bot.
Prompt Confirmation: View & Confirm Prebuilt Prompt
Bot Settings: Part 3 - Temperature
Control the creativity or precision of your bot responses:0.0 – 0.3: Very accurate and focused0.4 – 0.7: Balanced response generation0.8 – 1.0: More imaginative and open-ended
Bot Settings: Adjusting Response Temperature
Starter Questions
Let users quickly start conversations with predefined questions.How to Add Starter Questions
- Go to Bot Settings → Starter Questions
- Add up to 4 questions relevant to your bot
- Click Add and then Save
Starter Questions: Configuration Screen
Starter Questions: Configure Screen
Starter Questions: Display in Playground
Query Parameters
Query parameters allow you to inject dynamic data — like user ID, department, or context — directly into your bot’s logic.How to Add Query Parameters
- Go to Bot Settings
- Click Add Query Parameter
- Provide a name and reference in your prompt
- Save the changes
Query Parameters: Configuration in Settings
Query Parameters: Visible in Playground
🎯 Semantic Search Similarity
Control how precisely the bot matches your knowledge base.Relevance Thresholds
≥ 0.2: Broad, flexible match≥ 0.5: Moderate contextual relevance≥ 0.7: Strict precision
Semantic Scoring: Changing the Match Threshold
📩 Lead Collection
You can now enable lead collection directly from the Settings panel.How it Works
- When Enable Lead Collection is turned on, a contact form will be shown inside the chatbot widget.
- This form gathers user information like name, email, and optional notes.
- It helps convert casual visitors into potential leads or customers.
Settings: Lead Collection Toggle
Lead collection is a powerful way to capture qualified interest and convert chat interactions into actionable sales or support opportunities.
Configure these settings thoughtfully to ensure your bot delivers helpful, relevant, and contextually aware responses every time.