Articles in this section

User Guide for Calculus AI Ask Calculus AI Calculus AI Prompt Builder Data Shield in Generative AI Designer RAG Model in Generative AI Designer GenAI Setup in Generative AI Designer GenAI Token Usage in Generative AI Designer GenAI Queries in Generative AI Designer Natural Language Query (NLQ) Deal Health - A Calculus AI Feature Calculus GPT FAQs Using GPT features in Vtiger Calculus

GenAI Analytics in Generative AI Designer

In this article, you will learn about GenAI Analytics in Generative Designer.

Vinusha Balasubramanian

26 May, 2026 - Updated 5 months ago

Feature Availability

Vtiger Editions: One Growth | One Professional | One Enterprise | One AI

Introduction

GenAI Analytics in Vtiger CRM provides a centralized view of how Generative AI features are being used and how effectively they are responding to user queries.

It helps you to analyze chatbot performance using both visual insights and numeric data. By reviewing analytics, organizations can understand how many queries are being handled, what types of queries are being asked, how responses are being evaluated, and where improvements are needed.

GenAI Analytics is useful for monitoring AI performance over time and identifying areas where prompts, FAQs, source content, or AI configurations need to be improved.

GenAI Analytics in Vtiger CRM

GenAI Analytics is a reporting and performance-monitoring feature in the Generative AI Designer.

It provides dashboards and metrics that help you understand how your AI-powered chatbot or AI system is performing based on actual user interactions.

It allows you to analyze:

Total number of AI queries
Query review status
Types of AI responses used
Query acceptance trends over time
AI performance using visual charts and metrics

In Vtiger CRM, whenever a query is reviewed or categorized in GenAI Queries, the related metrics are reflected in GenAI Analytics. This helps teams track how well the AI is performing and how response quality changes over time.

Use Case

FreshCart E-commerce uses Vtiger’s AI chatbot to help customers with common support questions related to products, delivery timelines, and order information.

Customers frequently ask questions such as:

Is this product available?
What is the delivery time?
How can I change my order?

The AI chatbot handles these queries using configured prompts, FAQs, knowledge base content, and AI-generated responses.

The support team at FreshCart uses GenAI Analytics to monitor how well the chatbot is handling these interactions.

By reviewing the dashboard, the team notices that:

A large number of queries are marked as To be Reviewed
Many queries are being handled as GPT Queries
The acceptance rate for some product-related queries is low

To improve performance, the team takes the following actions:

Reviews pending queries in GenAI Queries
Improves prompts for product-related questions
Adds or updates FAQs for repeated customer questions
Trains the related RAG Models so the updated content is available in future responses

Over time, FreshCart sees the following outcomes:

Increase in accepted AI responses
Reduction in pending reviews
Better use of structured knowledge sources
Improved customer experience and chatbot accuracy

Benefits of GenAI Analytics

The benefits of using GenAI Analytics are:

Provides visibility into chatbot and AI performance
Helps identify how AI is handling user queries
Displays both visual and numeric performance data
Helps measure response quality over time
Supports data-driven AI optimization
Helps improve prompts, FAQs, and knowledge sources
Improves the overall user experience

In this article, you will learn about:

Accessing GenAI Analytics
Understanding the GenAI Analytics Dashboard

Key Terminology

Fields	Description
GenAI Analytics	The A dashboard that provides insights into AI query performance, usage trends, and response quality.that is related to a Contact.
Generative AI Designer	A platform in Vtiger CRM used to configure and manage AI features and analytics.
Bot Query	A user query processed by the AI system.
Query Status	The evaluation state of a query, such as Not Rated, To be Reviewed, or Accepted.

Accessing GenAI Analytics

Before accessing the GenAI Analytics, ensure the Calculus AI Add-on is installed from the Extension Store > Add-ons.

Follow these steps to access the GenAI Analytics page:

Log in to the CRM.
Click the main Menu.
Go to Platform.
Select Generative AI Designer. The Generative AI Designer page opens.

Click the GenAI Setup tab. The GenAI Setup page opens.

You will be redirected to a dashboard displaying reports and visual analytics.

Components of the Analytics Dashboard

The GenAI Analytics dashboard provides visual representations of bot activity and performance. It includes summary views, graphical reports, and time-based analysis to help you understand how users interact with AI and how the system responds.

The dashboard is divided into multiple sections, each focusing on a specific aspect of AI performance.

Understanding Dashboard Components

Bot Queries Record Summary

The Bot Queries Record Summary provides a high-level overview of all queries processed by the AI system.

It visually represents the distribution of queries based on their current status.

Key highlights:

Displays total bot queries.
Shows how many queries are reviewed vs pending.
Helps identify backlog in query evaluation

Status Classification of Queries

Each bot query is categorized based on its evaluation status. These statuses help track the effectiveness of AI responses.

Common statuses include:

Not Rated: Queries that have not yet been evaluated by users or administrators.
To be Reviewed: Queries that require manual review for quality assessment.
Accepted: Responses that are considered accurate and useful.
Rejected (if applicable): Responses that did not meet expectations.
FAQ Created: Queries converted into new FAQ entries.
FAQ Updated: Existing FAQs improved using AI responses.

Queries by Type (Input Type Analysis)

This section displays a breakdown of queries based on how they are processed by the AI system.

Types of queries include:

KB Query: Queries answered using the knowledge base.
Data Query: Queries that fetch data from CRM records.
Record Creation: Queries that trigger the creation of new records.
Record Query: Queries related to existing CRM records.
GPT Query: General AI-generated responses without structured data dependency.

Insights provided:

Identifies the most frequently used query types.
Helps understand user behaviour and intent.
Assists in optimizing AI configurations.

Queries Accepted by Date

This section provides a time-based analysis of accepted AI responses.

Key features:

Displays accepted queries by date.
Helps track trends in AI performance over time.

Insights provided:

Improvement in response accuracy.
Identification of periods with low acceptance.
Impact of prompt updates or training changes.

Date Range Filter

The dashboard includes a date range selector that allows you to filter analytics data.

Key capabilities:

Select custom date ranges.
Analyze performance within specific periods.
Compare trends across different timeframes.

Usage:

Evaluate AI performance after configuration changes.
Monitor weekly or monthly trends.

Best Practices

Follow these best practices to get the most out of GenAI Analytics:

Review analytics data regularly.
Prioritize queries marked as To be Reviewed.
Reduce dependency on GPT Queries by strengthening KB content.
Continuously refine prompts based on rejection trends.
Use date filters to measure the impact of changes.
Maintain clean and updated training data.

Reference

GenAI Queries in Generative AI Designer GenAI Setup in Generative AI Designer GenAI Token Usage in Generative AI Designer RAG Model in Generative AI Designer Data Shield in Generative AI Designer