Any AI agent is adept in solving objective questions and is very simple. But when an AI agent is used for continuous interaction and workflows to solve a problem, then the AI design will have to consider factors such as clarification of the issue , summarize the questions at appropriate stages, managing the memory from previous interactions, focus on the goal which is the very purpose of the interaction, more importantly empathizing with the user etc to ensure the AI agent is helpful and focused and efficient in addressing the problem.
I can think of a process which I was planning to implement in my company, and this question really picks my mind to consider many things though my plan is to start small and focus to a specific area.
Let’s say, I have developed an AI agent to address user issues related to invoicing.
Going by the ticketing history, most of the invoice related issues will have the ticket description as “Not able to print invoice”
So, my AI agent will have to ask user to do some checks, based on the result of those checks, there will be some other checks and based on that some other action will be directed to the user. Sometimes it can go to 5 or 6 checks before identifying the root cause. This is basically emulating the manual trouble shooting by the support personnel. Let’s say a POC is as below.
AI Agent – Hello, how can I help you with your invoice related issue?
User – I cannot print invoice for an order
AI Agent – Do you intend to run invoices for all the lines in the order or specific lines?
User – Only one line in the order which must be urgently dispatched
AI Agent – Is the status of the order line at “58”
User – Yes
AI Agent – Do you see in the application any hold code for the order line you intend to invoice
User – No
AI Agent – Is there a price for the line you intend to invoice?
User – Yes
AI Agent – Can you give me the version of the invoice you ran?
User – INVSO3
AI Agent – Sorry, no version exists, please use version INVSO3I
User – it was a typo; I ran the correct version INVSO3I
AI Agent – will you be able to check the scheduled invoice date if it is today or lesser date?
User – I don’t know
AI Agent – Can you open application PSINV25U?
User – Sorry I don’t have access
AI Agent – Should we first create request for you to have access?
User – I need this to be resolved urgently
AI Agent – Sorry, please raise an IT ticket, so a support staff can assist you better.
From the above POC, what I see is the design of the AI agent is vey direct and straight forward, but after reading about this topic I need to tinker a bit the design so the AI Agent will also exhibit the following:
Being Empathetic, understanding user sentiments and respond accordingly: The user is in a hurry to take invoice print for the goods that must be dispatched from the warehouse. The trucks are waiting. So instead of “Do you intend to run invoices for all the lines in the order or specific lines”, I would recommend “Sorry to hear that, don’t worry we can resolve the issue together quickly”, would be a better response from AI that gives an assurance to the user and calms the user.
Summarize the issue for better user engagement and focus: Instead of asking for repeated checks in isolation, I think after couple of checks there could be a summarization like” the status is correct, there is price, there are no holds, still not able to invoice, interesting, bear with me for few more checks”. So, the user would be engaged and not frustrated, and the user will know the AI agent is analyzing and really trying to troubleshoot with the inputs of the user
Focus on goal though there are several checks and misleading inputs: Instead of asking user to solve the access issue, which was not the very purpose of the interaction , it could have said “ No problem, can I connect you with a support agent to resolve the invoice prints, so the issue will be resolved in the next 15 minutes, is it ok?” something like this I am wondering.
Also, I am thinking of making communication very efficient, which would require more iterations and use cases.
Overall, I feel using the above steps or techniques a conversational AI can navigate multiple step processes/workflows and emotionally charged interactions, effectively ensuring that the user feels engaged and the interaction is productive