top of page

Empowering Conversations: The Gen AI Chatbot Revolution

PRODUCT DESIGN | UX RESEARCH | UX DESIGN | USABILITY TEST 


The project aimed to develop a Gen AI-powered prompt based research chatbot for both chat and Voice agents to enhance customer support interactions and reduce cognitive load, providing immediate responses and improve user experience across various platforms by keeping humans in loop


Note: To comply with my non-disclosure agreement, I have omitted confidential information in this case study. All information in this case study is my own and does not necessarily reflect the views of the platform


Overview


Focused here was to revolutionize customer support by developing a sophisticated AI-driven assistant capable of providing real-time, accurate responses to customers across multiple platforms, including voice, chat, and POS systems.


It leverages multiple action bots framework using text and voice commands as prompts to guide the interaction, helping agents retrieve, analyze, and understand information efficiently.


Role: Senior UX Designer focused on creating the product strategy, collaborating with a cross-functional team, building experience and aligning it with all the capabilities.


Duration: January 2023 – June 2023


Tools & Technologies: Figma, Figjam, Google suite, Sketch, Invision



"Vision - Build Prompt based Research Assistant for Frontline teams  to review thousands of resources quickly and accurately in a personalized manner"


Step 1 - Understand

 

Problem Statement


In the rapidly evolving world of generative AI (Gen AI) chatbots, legacy chatbots were facing several challenges that can hinder the client's ability to provide competitive and efficient customer service.


Their current agent assistant were constrained by static responses, suffers from inefficiencies, high agent workload, inconsistent experiences, only delivering pre-programmed answers and unable to handle conversations beyond predefined inputs. Their inflexibility makes it difficult for agents to search for more complex queries.


 

Business Challenge


  1. Current Agent Assistants lack advanced NLP, leading to inaccurate responses and inconsistent support quality, frustrating customers and lowering satisfaction.


  2. Higher handoff rates to human agents and frequent maintenance increase costs and strain support resources.


  3. Without intelligent recommendations, the chatbot misses upsell and cross-sell potential, reducing engagement and loyalty.


  4. Difficulty integrating with new channels and handling complex interactions limits scalability and effectiveness.


  5. They suffer from inefficiencies and high agent workload.


  6. They deliver inconsistent experiences, providing only pre-programmed answers.


  7. They are unable to handle conversations beyond predefined inputs.


  8. Customers face long waiting times for support, resulting in frustration and decreased satisfaction.



Key Business Priority


  • Enhanced User Engagement

    It should deliver personalized interactions by leveraging the user’s history, preferences, and context, thereby enhancing customer satisfaction and loyalty.


  • High Accuracy and Relevance

    It should retain and understand context throughout interactions, enabling more relevant, accurate and meaningful responses. 


  • Reduce the cost to serve

    Become the primary destination for agents to look for anything to resolve customers issues.


  • Customer Retention and Upselling

    Implement features that allow the agent to proactively engage customers with relevant offers, upgrades, or service enhancements based on their usage patterns and preferences.



My Role


 I worked on this project as a Product Designer and was involved from the very initial stage that is setting up the vision and creating a product from scratch. Lets look at some of the phases of the project


To address these challenges, we focused on the vision and strategize the evolution of agent assistant with a Gen AI agentic chatbot that enhances  the customer experience, reduces cognitive load and provides consistent, high-quality support across all customer interactions.

Core Priorities


  • Focused on understanding user needs through research and testing.

  • Used Customer intent, Agent feedbacks, and call listening to identify, iterate and improve the chatbot's experience.

  • Designed to cater to user emotions and provide a human-like interaction.

  • Worked closely with all the business partner, stakeholders to align on goals and expectations.

  • Prioritized tasks build the strategy as per leadership Vision and delivered maximum value to agents and the business.




Goals & Objectives





Evolution of Agent assistant with the advance gen AI technology to reduce cognitive load and serve customer faster.

Our aim is to make support interactions smoother and more efficient. Reduce the number of support calls, boosting user satisfaction and improve response accuracy.


Product Strategy




The narrative


We want to transform the chatbot for reps and customer as a performance defining component for getting support to gain competitive advantage in the marketplace






Step 2 - Define


 


Approach & Methodologies







  • Understand

    Engage with stakeholders to define objectives, desired features, and performance goals. Shadow agents to understand workflows, pain points, and decision-making. Establish KPIs like AHT, FCR, and user satisfaction as success metrics. Develop user personas reflecting agents' roles, needs, and expertise.


  • Research

    Analyze the current Agent Assistant's capabilities, limitations, and performance to understand its effectiveness. Identify pain points experienced by both customers and agents within the existing voice support system. Gather insights from key stakeholders, including customer service agents, customers, and technical teams, to inform the improvement process.


  • Design

    Gathered insights through user interactions and workshops with agents and stakeholders to identify pain points, mapped workflows and key user journeys to find improvement opportunities, brainstormed and developed solutions, created interactive prototypes for initial testing, and conducted usability testing to refine chatbot interactions based on feedback.





Priorities

Objective
Key Actions
Expected Outcomes

Identify pain points and create prototypes

User research, User Persona, wireframing, prototyping

Comprehensive understanding of user needs

Refine prototypes and integrate features

User testing, iterative design, development

User-friendly interface, reduced error rate

Launch platform and optimize based on feedback

Platform launch, collect feedback, optimize

Higher agent productivity, improved CSAT




Who are the USERS?

  • Frontline Voice & Chat Agents

    These are the customer service representatives who connects with customer daily and help them solve their issues on call or through chat. They rely on chatbot interaction to understand the context of the customer's problem and provide appropriate solutions.







.



User Pain Point


  • Disjointed agent assistance platforms led to inconsistent experiences, increased handling times, and high error rates.

  • Complexity in using multiple systems resulted in steep learning curves for new agents

  • Users reported difficulty in finding relevant information quickly, leading to increased support calls. 

  • The chatbot provides irrelevant or incomplete answers, making it frustrating for users seeking quick solutions.

  • Interactions feel generic, with the chatbot unable to remember user history or adapt responses to individual needs

  • Predefined scripted responses, which slows down the conversation and prevents seamless issue resolution

  • When users have complex or multi-part questions, the chatbot struggles to keep context or respond accurately, requiring users to restate information.

  • Users may feel lost or abandoned if the chatbot does not provide updates or indicate that an issue is being handled, leading to a frustrating experience



Data Analysis


During the Data Analysis phase, we focused on gathering and interpreting key data from agent feedback, customer intents, and call listening. This analysis informed our design decisions and optimized chatbot performance. We identified user needs and preferences, pinpointed pain points, gathered behavioral insights, and validated key assumptions.



Stakeholders Interview


In the stakeholder interviews, we aimed to align the Gen AI chatbot's design and functionality with business objectives and operational needs. We conducted open-ended interviews, encouraging stakeholders to share insights on current workflows, desired improvements, and priorities. Findings were synthesized to identify recurring themes and validate assumptions, such as existing challenges and new requirements.


We collaborated with stakeholders again to finalize measurable goals, including Average Handling Time (AHT), First Contact Resolution (FCR), and customer satisfaction targets. Insights were then summarized in a report and shared with project teams to ensure clarity and alignment.



UX Audit


During the UX audit, we aimed to identify usability issues and optimize the agent experience across chat and voice interfaces. This audit highlighted areas needing refinement to enhance usability, efficiency, and overall agent satisfaction. We conducted task analysis, usability testing with superusers, and a review of the chatbot interface for accessibility. Additionally, we:

  • Analyzed consistency and reliability of chatbot responses across scenarios.

  • Reviewed the information presented, focusing on elements that might cause cognitive overload.

  • Assessed the chatbot’s alignment with agent workflows.

  • Evaluated layout and navigation to ensure agents could access information quickly.

  • Identified instances of insufficient feedback or unclear error messages.

  • Audited business KPIs to gauge alignment with performance goals.


The UX audit provided actionable insights that guided design improvements, making the Gen AI chatbot a more intuitive and supportive tool for agents. This rigorous assessment helped us closely align the chatbot’s functionality with agent needs, enhancing satisfaction and effectiveness.


Competitive Analysis


The Goal was to understand the patterns, insights, technology of top competitors and benchmark the approach by identifying techniques or features they offer, learn how they provide a better user experience, and discover potential opportunities for us


ChatGpt
Google Gemini
Microsoft Copilot

ChatGPT is a prompt driven platform and has a strong conversational abilities and broad knowledge base. 

Google Gemini is also a prompt driven AI interface, but it stands out for its multimodal capabilities, seamlessly handling both text and images.

Microsoft Copilot leverages the power of Microsoft’s cloud and productivity tools, integrating OpenAI’s technology to deliver enhanced solutions tailored for enterprise needs.

It is an independent Platform and is paired with a user-friendly interface that makes it accessible for a wide range of applications.

It is integrated within Google's ecosystem.

Its seamless integration with Microsoft products, including Microsoft 365, makes it a robust, enterprise-ready tool with strong cloud support.

Its API is particularly noted for ease of use, allowing developers to integrate conversational AI and language generation into various platforms.

Its advanced conversational abilities and strong integration with Google services enhance its appeal for complex, multi-faceted tasks.

However, its reliance on OpenAI’s technology and limited customization options for non-Microsoft environments can be seen as drawbacks.

It is limited to text-only interactions, lacking multimodal capabilities, and its performance can vary on specific queries.... more+

It has multiple features like, multiple conversation, conversation history, prompt suggestions, multilingual which show personalize results as per users needs... more+

more+


  •  Many More+



Evolution of Agent assistant with the advance gen AI technology to reduce cognitive load and serve customer faster.



Step 3 - Design

 


Phase 1

We leveraged Gen AI to optimize agent performance across Voice, Chat, and POS platforms, improving customer service and operational efficiency. The Research Assistant provides real-time support with instant answers from knowledge sources using prompts and keyword recognition.


To introduce a Gen AI-powered chatbot, we designed a cohesive and intuitive experience that streamlines task completion for agents. The chatbot incorporates features like insightful prompts, dynamic search suggestions, proactive notifications, and a user-friendly interface. Built with scalability in mind, it supports seamless integration of future features and functionalities to adapt to evolving needs.



Bringing Ideas to Life



Prioritization


After the workshop , we identified and prioritize the ideas and concepts generated during ideation. we evaluated each idea based on criteria such as feasibility, impact on users, and alignment with business goals. Prioritization helps us focus efforts on the most promising concepts.


Customer Case


Identified customer cases based on agents conversation and build the experience. It includes creating widgets based on guidelines, defining the paths to ensure reps can easily find information and resolve customer queries.


Feature Benchmarking


Features were prioritized based on their value to agents, business impact, technical feasibility, and innovation. capabilities—such as insightful prompts, keywords, dynamic search suggestions, proactive notifications, transcription, Quick tool launch and more were tailored for agent workflows.


Performance metrics like response speed, accuracy, and engagement are established to measure success, while scalability ensures future integration of additional functionalities.


Conceptualizing


After prioritizing the ideas, we moved on to explore various ways to implement these ideas. This phase encourages creativity and generates multiple design concepts or solutions. It involves sketching, brainstorming, and sometimes creating rough prototypes to visualize different approaches.


Integration with Adjacent Features


Identified Adjacent features which can help create a more robust, efficient, and supportive environment for agents, enhancing productivity and improving customer satisfaction by reducing time spent switching between systems and by providing all essential tools in one place.


  • Automated Workflows

    Pre-built workflows for routine tasks (like customer verification, troubleshooting steps, or follow-ups) allow agents to complete tasks with minimal effort, saving time and ensuring consistency.


  • Suggested Replies and Next Steps

    Based on the conversation context, the assistant can suggest relevant responses or actions to guide agents efficiently through customer interactions.


  • Knowledge Base Search and Article Recommendations

    Real-time access to knowledge base articles tailored to the current query ensures agents can quickly access detailed information and reduce research time.


  • Case and Ticket Management

    Integration with case management enables agents to create, update, and close cases directly from the chatbot interface, keeping support records accurate and centralized.


  • Escalation and Handoff Tools

    One-click escalation or handoff to specialized departments or supervisors ensures complex issues are routed to the right resources without delay.


  • Task Management and Reminders

    Task lists, reminders, and follow-up notifications ensure agents remember key actions and follow through with customers as needed.


  • Product Recommendations and Upsell Options

    In retail or sales contexts, the assistant could suggest product recommendations, upgrades, or discounts based on customer interactions, enabling agents to cross-sell or upsell effectively.




Product & Capabilities





Component & Composition


Adaptive Prompts

Designed prompts to adapt based on user context, previous interactions, and real-time data, allowing agents to access relevant information faster.

Color Theme

Focused on creating both dark and light color theme based components and chatbot library

Notification Management

Built a notification system with adjustable priority levels and reminders, allowing agents to manage alerts without being overwhelmed.

Error Prevention and Recovery

Integrated clear error messages and recovery options to help agents quickly address mistakes, reducing cognitive load and enhancing task efficiency.

Micro Animation

Created multiple micro animations as well, wherever required based on the status of the query, result or notifications

User Feedback Loop

Embedded feedback mechanisms where agents can rate or respond to chatbot interactions, providing insights for continuous improvement and refinement.

Responsive Design

Ensured the layout adapts seamlessly across different screen sizes and devices (desktop, tablet, mobile) to support agents working from varied setups.

Progressive Disclosure

Applied progressive disclosure techniques to only show complex information when needed, keeping the layout clean and focused while reducing information overload.

Core Components

Designed widgets and components tailored to specific use cases, ensuring alignment with brand guidelines and consistency in behavior across interactions.

Breathing Space

Maintained a 2% spacing between components to enhance readability, ensuring a balanced and visually comfortable layout.

Micro Animations

Integrated subtle animations to indicate query status, results, or notifications, adding clarity and a smooth user experience.

Quick Actions

Added quick actions and shortcuts to streamline repetitive tasks, improving agent productivity by reducing clicks and interactions.


Building the Solution


We reviewed existing data and agent feedback from the newly released proactive bot and its intents.


  • Identify Relevant Business Cases: Analyze rep searches and customer intent to pinpoint key business cases.

  • Understand Customer Inquiries: Learn why customers contact the client and identify the most frequently asked queries.

  • Evaluate Agent Feedback: Understand what’s working well and identify areas for improvement based on agent feedback.


Solution Architecture & Framework


We connected with the dev team to understand the capabilities, the chatbot leveraged a modular architecture, learned how they are going to integrate conversational AI models for for all the capabilities, response generation, and real-time data processing. We looked into the current API structure and how it seamlessly connect with backend data sources, enabling access to critical information in real-time and enhancing response accuracy across chat and voice platforms.


Prompt Design


We crafted contextually aware prompts that adapt based on the agent’s workflow, Customer context, and previous interactions. These prompts are concise and directed, minimizing cognitive load while ensuring agents get the exact information they need to respond effectively.


Flow Optimization


User journeys were also mapped out, allowing for smooth transitions between prompts, suggestions, and notifications. This flow optimization reduced friction, ensuring agents could quickly respond to customer inquiries without interruption.


Component Design


  • Core components—such as search suggestions, proactive notifications, and query responses—were designed following brand guidelines to maintain a consistent look and feel. Each component was developed with a clear purpose, maximizing usability in specific agent tasks.

  • We introduced subtle animations for visual feedback on actions, such as query status or notifications, adding a layer of responsiveness that kept agents informed without overwhelming them.

  • To support agents across varied working conditions, we developed components for both light and dark themes. This adaptability increased visual comfort and accessibility.


Patterns & Insights


  • Gen AI + search
    • Client Knowledge base

    • All Content type and categorization

    • single search window

    • suggestions


  • Semantic search
    • Relevant & accurate results

    • specific & personalized

    • Simple & Synthesized

    • Typeahead suggestion

    • suggestive search

    • search suggestion


  • Prompts, Keywords
    • Natural Questions and responses

    • Wider use cases

    • Case management and connected workflow

    • Customer history and proactive listen


Implementation and Collaboration


Collaboration was the key for bringing this solution to life. Working closely with engineering, product, and support teams, we maintained consistent alignment on design requirements and technical feasibility. Agile sprints and regular feedback cycles enabled rapid iteration and refinement, ensuring the final product met agent needs and business goals cohesively.






Stakeholders review and socializing with all the platform owners


To ensure alignment and buy-in from all stakeholders across Voice, Chat, POS, and related systems, we began socializing the Gen AI Chatbot prototype with platform owners, business leads, technical teams, and user representatives.


  • Customize presentations to show how the Gen AI assistant aligns with platform goals and addresses pain points.

  • Provided key features, benefits, and how the design meets user needs and business objectives.

  • Hosted sessions to demonstrate how the Gen AI assistant integrates with each platform.

  • Encouraged discussions to gather feedback, concerns, and suggestions for improvements.

  • Shared a clickable prototype showcasing user journeys and integrations relevant to each platform.

  • Present tailored use cases (e.g., Voice agents troubleshooting or POS agents accessing customer history).

  • Refined and Iterated the prototype based on feedback, addressing concerns and improving features.


Phase 2


Usability study


We aimed to understand how the Gen AI Research Assistant aligns with the support service rep’s mindset on the Voice platform. To achieve this, we set up a usability study and created a document outlining the key areas to cover and the specific data we wanted to gather.


Through all the previous research we discovered some scenarios and situations that we can test and validate with the Reps



The process we followed for conducting a usability study with prototypes involved organizing a group study moderated by a facilitator


  • We Finalized the interactive prototypes to test key functionalities and scenarios.

  • Define clear goals for the study, such as understanding usability, effectiveness, and alignment with agent needs.

  • Equip the moderator with study guidelines, key questions, and prompts to ensure consistency

  • Ensure the group has access to the prototypes and any required devices or tools.

  • Voice agent from India and US were the participant of the study

  • Focus group study on refreshed Gen Ai chatbot facilitated by the moderator

  • 1 hour session where participants were asked to think out loud while going through the prototype

  • moderator probed for further insights

  • Reporting mechanism was through feedback sheet




  1. Divided Ease of use in the four use case which only highlighted the experience and behavior of the Gen AI chatbot

  • Complex Queries

  • Voice Input

  • Searching in Chatbot

  • Dark & Light mode



  1. Developed multiple use case prototypes covering key business scenarios related to "how to ask and find." These prototypes helped us evaluate whether agents could effectively ask questions and find the necessary answers, focusing on addressing their immediate needs during daily tasks.

  • Billing Inquiries

  • Device Eligibility

  • Policy Check

  • Promo Failure

  • Account Changes

  • TYS Request

  • more+




  1. For proactive notifications, we created two different micro-animations to showcase the behavior of the nudges. We shared the prototype with agents and gathered their feedback through targeted questions.



High level Key Takeaway





Building the roadmap


Analyze Usability Results


  1. Consolidate Findings

    Gather all feedback from the usability study and categorize insights into themes (e.g., usability issues, feature requests, workflow gaps).


  2. Identify Key Improvements

    Highlight critical issues to address and prioritize based on their impact on agent workflows and customer satisfaction.


  3. Stakeholder Alignment

    Present the findings to stakeholders and align on the next steps, ensuring all parties agree on the priorities and roadmap.



Design Refinement and Validation


  1. Prototype Refinement

    Update the chatbot prototype to incorporate usability feedback, focusing on intuitive design, clear workflows, and effective nudge behaviors.


  2. Validation Testing

    Conduct a follow-up usability test with refined prototypes to validate improvements and ensure alignment with user expectations.


  3. Define Design Systems

    Standardize design patterns, micro-animations, and interaction flows for consistency and scalability.



Build Core Chatbot Features


  1. Core Functionality Development
    1. Implement the chatbot's foundational features, such as:

      • Real-Time Assistance: Providing immediate answers using knowledge sources.

      • Proactive Notifications: Nudges and alerts for critical information.

      • Dynamic Search Suggestions: Context-aware recommendations for agent queries.


  2. Integration with Platforms

    Seamlessly integrate the chatbot into Voice, Chat, and POS platforms, ensuring it aligns with each platform's unique workflows.


  3. Back-End Enhancements

    Optimize the AI engine for natural language understanding (NLU), intent recognition, and knowledge retrieval.



Expand Features and Adjacent Tools


  1. Develop Adjacent Features

    Add complementary functionalities, such as case management, customer sentiment analysis, and task reminders.


  2. Scalability Design

    Build the chatbot to accommodate future feature additions and platform expansions without major overhauls.



Testing and Deployment


  1. Beta Testing

    Launch a beta version for a limited group of agents to gather real-world feedback.


  2. Performance Monitoring

    Track metrics like response time, accuracy, and agent adoption rates to ensure performance aligns with expectations.


  3. Iterative Improvements

    Address issues identified during beta testing and refine features as needed.



Full Rollout and Feedback Loop


  1. Training and Onboarding

    Conduct training sessions for agents to familiarize them with the chatbot's features and workflows.


  2. Gradual Rollout

    Deploy the chatbot in phases across platforms to ensure a smooth transition.


  3. Continuous Feedback Loop

    Regularly gather agent feedback to identify new improvement opportunities and refine the chatbot over time.



Measure Impact and Plan Future Updates


  1. Monitor KPIs

    Evaluate metrics such as average handling time (AHT), first-call resolution (FCR), and agent satisfaction to measure success.


  2. Plan Future Enhancements

    Use collected data and ongoing feedback to define the next phase of updates and improvements, ensuring the chatbot evolves with business and agent needs.




Building the knowledge base


We analyzed data from agent searches, customer intents, and feedback to pinpoint the most frequent and impactful scenarios.


This involved reviewing call logs, chat transcripts, Call listening and POS interactions to understand common queries and challenges faced by agents. By categorizing these use cases based on frequency, complexity, and business impact, we prioritized those that align with critical agent workflows and customer needs.


This comprehensive list forms the foundation for designing a chatbot that addresses real-world scenarios effectively.


Along with Voice, designed for retail platform with focusing on 60 intent and customer cases related to POS research assistant and released it in Oct to over 20K Agents and Migrated 60 Intents



Continuous improvement


The AI model was continuously updated and trained using real-world interactions to enhance its understanding and response accuracy. Identified issues were addressed, with improvements made to natural language understanding and the escalation process.


 


Outcomes


Key Performance Metrics

Metrics
Results

Average Handling Time

reduced by an average of 2 minutes

Customer Satisfaction

Improved from 78% to 89%.

Agent Productivity

Increased by 35%

Response Accuracy

Increased to 92%

Support Call Volume

Reduced by 35%

Training Time for New Agents

Decreased by 35%.



Tracking method

Method
Tool Used
Purpose

Performance Analytics

Adobe

Track handling time and case volume

User Feedback

Spreadsheets, feedback forms/ mechanism

Measure satisfaction scores

Usability Testing

Internal team

Evaluated interface changes


Qualitative Results


  • Agents report the system as intuitive.

  • Participation increased by 40%, with support for complex queries.

  • AI system adapts to new queries and scenarios.

  • Fewer support tickets, faster responses, and higher resolution rates.

  • Increased feedback and survey participation from agents.

  • Higher engagement with promotions and positive reviews.

  • High usability scores with reduced cognitive load.

  • Strong user trust, privacy compliance, and secure data handling.



Key Challenges


1 Balancing different  stakeholder priorities.

2 Navigating technical limitations of legacy systems.

3 Ensuring user adoption through effective training.

4 Integrating the new Gen AI assistant with clients existing infrastructure. This required extensive collaboration with the dev teams to ensure seamless experience

5 Ensuring that the AI assistant handled sensitive information appropriately and maintained customer privacy was a constant priority. This involved working closely with legal and compliance teams.

6 The goal was to build a chatbot keeping human in loop  while making a balance where, Chatbot can act as a personal assistant and agent is leading the whole conversation with the customer.

7 Training the Gen AI model to handle the vast array of reps queries was time-consuming and required a large dataset. Ensuring the model’s accuracy across diverse scenarios was a continuous process.


Key Learnings


1 Stakeholder Engagement: Regular updates and workshops fostered alignment.

2 Early usability testing helped identify and resolve issues.

3 Using analytics effectively guided design improvements.

4 User- Continuously involving end-users in the design process led to a more effective and user-friendly product. Understanding their needs and challenges helped in creating a solution that genuinely addressed pain points.

5 Regular testing and iterating based on feedback ensured that the assistant continuously improved and adapted to user needs.

6 Working closely with various teams, including AI engineers, IT, legal, and customer support, was crucial in creating a product that was not only functional but also scalable and compliant with all regulations.

7 Designing with scalability in mind ensured that the assistant could be rolled out to a broader audience without significant rework.


Conclusion


The Evolution of Agent Assistant into a Gen AI chatbot for customer support on the voice & chat platform was a comprehensive process that leveraged the design thinking methodology. By focusing on empathy, ideation, prototyping, and testing, we created a product that significantly improved customer experience, reduced call handling times, and allowed support agents to focus on more complex issues. The project highlighted the importance of user-centered design, continuous feedback, and cross-functional collaboration in developing successful AI-driven products.



Next Steps


  • Post-Launch Optimization: Ongoing user feedback collection and iterative improvements.

  • Leverage AI for enhanced support capabilities.

  • Integrate additional tools quick tools, automating the task expanding the knowledge bases and smart suggestions

  • Integrating the Chatbot to other assisted platforms as well..


Connect with me  

© 2024 by Antra Sharma. Powered and secured by Wix

bottom of page