Building EVA for Nedgroup Investments

We built the Atura platform with abstraction in mind so that we can easily build customised client instances by leveraging our core infrastructure.

The EVA conversation flows were mocked-up on paper without any constraint, and then translated to the running AI Assistant visible today on the Nedgroup Investments website. Since our bots are built with C# code running on the MS Bot Framework, they are extremely flexible and fast to build.

Deep integration into Nedgroup Investments systems AI assistants without context are boring and have limited practical usefulness. We focus on integrating with client back-end systems to give the assistant as much user context as possible while keeping privacy and security in mind.

EVA integrates with the Nedgroup Investments web services via standardised HTTPS protocols, giving her access to user data (context) and the ability to perform financial transactions on behalf of the user. These transactions include:

Adding funds to accounts Requesting statements Requesting tax certificates Checking balances

EVA active

AI assistants may be able to answer all questions in future, but that is not possible yet. In situations where EVA is unsure, she gives the user the option to chat to a client services agent, while still in the chat window, so that a real person can help resolve issues and answer questions. When the agent has finished helping the user, control is passed back to EVA.

Following is a screenshot of the agent service desk with new and unresolved “conversations” awaiting attention:

EVA allows users to type questions in plain text. Internally we send the user’s text to Microsoft’s LUIS service that uses machine learning models to translate the user’s query into an “Intent”. This allows the

user to ask things like: “How risky is your guraded[sic] fund?” and EVA will know the user is asking about the “Risk Category” for the “Nedgroup Investments Guarded Fund”.

Machine learning

Conversation context

Remembering

When logging in, EVA requests the user’s ID number, then prompts for approval via the user’s pre-existing cell phone number on the back-end system.

No username or password is required, because the user has to accept/reject the login request on their mobile device:

Log in

Some input is better suited for entry on a typical web form, as certain types of functionality will be very cumbersome to represent via text chat. EVA supports rendering “web views” which are custom web pages embedded in the chat window.

Web view

It is possible for us to expose EVA over channels other than chat widgets with minimal changes to the code. This is possible because we use the MS Bot Framework as an intermediate layer that translates messages to the appropriate format for different channels.

For example, our webchat channel shows richly formatted buttons, while rendering plain text in WhatsApp:

In webchat

Atura has a reporting function that gives insight to: conversation duration, messages per support agent, nr of help requests within and out of office hours, most popular “Intents”, etc.