Utilised an AI Chatbot to Decrease Customer Support Tickets by 89%

Our client’s customers previously accessed limited reports through the platform’s dashboard, requiring them to contact customer support for other metrics. This lack of customization resulted in delays and dissatisfaction. To fix this, they partnered with Arrk’s AI Engineering team to create an AI-enabled chatbot. The chatbot handles dynamic queries, quickly presenting complex statistics from the database, improving the customer experience and solving the previous issue of delayed replies and high turnaround times for human-generated tailored reports.


This client is a services-based company, providing outsourced support in various sectors including Telecom, Automotive, Insurance, Finance, Banking, Accounting, HR, and Recruitment. Our Client is one of the top companies with a client base of 5000+ companies across multiple countries and continues to grow at an exceptional rate.

Problem Statement

Using the platform’s inbuilt dashboard, their customers could access reports related to various back-office processes.

However, these reports had limitations, often forcing customers to contact the client’s customer support team for insights and data beyond these reports. Customers couldn’t drill down custom reports easily, leading to repeated contact with customer support for other details.

Ultimately, clients had to either email tailored report requests to the support team, create service desk tickets, or endure long phone queues until a customer service representative assisted them.

This often resulted in late initial responses and extended turnaround times for getting tailored reports, eventually leading to a diminished customer experience and client attrition.

Recognizing the need for an expandable solution, they partnered with Arrk to build an AI enabled based chatbot able to handle dynamic queries and supply timely, contextually appropriate information from the database.

Custom Reports

Extended Turnaround Times

AI-based Chatbot

Solution Development

We started with a two-week, intensive EmbArrk™ project discovery workshop to gather and elaborate requirements and specifications and to establish consensus among all stakeholders.

After careful consideration, we decided to have three separate Scrum teams, one for each business component.

Arrk’s AI Engineering team selected the relevant chatbot platform in combination with Google Cloud Dialogflow to structure the AI enabled chatbot, leveraging the combination to safeguard secure data integration, improve scalability, and deliver a unified real-time, customer experience.

We trained the AI enabled chatbot to understand user query intents and context using Natural Language Processing (NLP).

Once trained on over 250 different intents and 1250 utterances, the chatbot could manage a diverse range of queries.

Natural Language Processing enabled the AI enabled chatbot to obtain facts from queries and recall data from systems.

Integration with the client’s backend systems via APIs allowed the chatbot to retrieve and supply relevant data-rich responses with a very low failure rate.

In cases of complicated queries beyond the bot’s training, it smoothly transitioned the discussion to an individual human representative, ensuring a consistent client experience.

The AI-enabled chatbot was introduced to clients in a phased manner, and its success led to an extension to voice-based virtual assistants.

EmbArrk™ Workshop

Secure Data Integration

Voice-based Virtual Assistants


  • The AI chatbot was embedded within the client’s product dashboard, accessible to users only after validation to protect sensitive data.
  • Once authenticated, users can input industry-related queries.
  • The smart AI enabled solution identifies the user’s query intent and retrieves the correct answer from the client’s database.
  • Users can frame queries in numerous ways and still receive appropriate responses, thanks to the chatbot’s ability to understand various statements of the same query while maintaining context.
  • 89% reduction in regular inbound customer queries.
  • 95% increase in query resolution speed.
  • Over 1,000,000 queries are answered annually by the chatbot.
  • Thousands of human work hours saved annually.
  • Delivered data enriched query results from multiple systems

User Authentication

Faster Query Resolution

High Query Response Rate

More of Our Case Studies