Smita Vaval

If we need to visualize a futuristic AI which has evolved across these years, will take a scenario of AI Agent in service industry - Travel Agency - The AI Agent while interacting with customers having previous history of the specific customer choice, preference, visited places, etc. can provide plans and options. Also basis customer replies, can do sentiment analysis to change the proposals and make necessary changes to ensure customer opts for taking the plans from this travel agency. Also this AI has advanced NLP and understanding which would help seamless communication with clients and customers from diverse backgrounds. The one risk which we need to manage is protecting customer data and security.

Per my understanding AI would face this kind of trade off in most of the service industries where the AI agent need to handle 2 or more objectives such as time bound, accurate, precise, customer delight, etc. Taking example of Customer Service in E-commerce.. Scenario : Customer queries are been handled by an AI Agent. Here the AI needs to manage response time with accurate and precise replies to queries regarding orders, deliveries, return, refund, etc. How you would guide the AI to handle the trade-off – 1. Identify the Issue/query type : AI should first recognize the type of query if it’s an order status, return, refund or just an information. 2. Assess the urgency : Basis the query and customer responses assess the urgency attached to the query 3. Assess the complexity: such as order status can be simpler to handle whereas lost or refund may need additional information or time to reply. What logic, rules, or signals would help it make the right call? 1. Rules: Set the priority rules such as simpler queries like order status to prioritize for quicker reply over the queries like lost items or refund may need additional information or time to reply 2.Logic: For the prioritized queries response may be shorter with predetermined pattern of text such as delivery time, tracking or details of delivery agent etc. For queries requiring longer time to add follow up question to gain more understanding and give more detailed and precise reply including adding steps needed by customers to take 3. Signals: Customer Response (Important to assess what the customer says during the conversation. Basis those sentiments replies may need changes) and Response Time (Overall response time to be checked to ensure it gives quicker responses per the urgency)

Our internal team has developed an AI-based platform to manage the internal queries raised by team members as part of managing their activities. The knowledge base (KB) is collated from training material, standard operating processes, client feedback, and other relevant sources. However, the AI may need to escalate scenario-based questions that are not part of the KB to humans for resolution. In such cases, the AI can learn from these provided solutions by: Analyzing the given responses. Identifying processes where such exceptions occur frequently. Measuring the time taken for responses. Detecting any patterns or rules in the responses collected through such exceptions. Tracking the frequency of these exceptions. Assessing the need to update the KB based on the frequency and nature of exceptions. Monitoring further queries that arise post such exception cases. This approach ensures continuous improvement of the AI system, enhancing its ability to handle a wider range of queries autonomously over time.

In one of our account, team has implemented a chat bot to handle customer queries as well as escalations. This chat bot works very efficiently to capture client input, provide tracking number, share it with BPM team members, does follow up and if necessary escalations till the issue is not resolved or provide resolution back to client. Also this chat bot backend data has analysis feature. The one step where we need AI to escalate to human is for doing a Root cause analysis. While basis previous data may give certain inputs for Root Cause Analysis but it has to involve human to get more human inputs which data base cannot provide.

Team connects including meetings with team members, one on one discussions, grievance discussions, Team events are 'too human' to hand over to AI. While AI will be helpful contributor to organize, provide important data inputs, manage the action items, help for ideas etc.