Working together with Accenture, IPsoft conducted a project for a large oil and gas company in order to assess whether it would be possible to use Amelia to help the company provide a prompt and more efficient way of answering invoicing queries from its suppliers. In order to provide a notable level of benefit, Amelia was fully trained in the process to be followed in order to respond to the top 25% of questions received from more than 500 suppliers.
In order to provide the most effective first response, Amelia was integrated into an existing self service portal for suppliers. As a secure log in is required, it meant that whenever a supplier initiated a conversation, Amelia would instantly be aware of whom she was speaking with and which organization they represented. This single sign-on approach opened up the possibility of providing personal context to every interaction and the ability to eliminate time wasting basic questions. It also allowed for varying levels of access to information to be applied depending on the individual participating in the conversation.
Upon contact using a live chat function, Amelia reconfirmed the identity of the supplier in her greeting, before answering questions in the same way as a human service desk agent. Typical questions included:
- I received a payment of $512. What’s it for?
- I would like to know the status of an invoice.
- When will my invoice be paid?
As you would expect of a human agent, Amelia then asked questions in order to establish exactly which invoice was being referring to. For example, she would ask:
- What is the invoice number?
- What date was invoice issued?
- What amount was the invoice for?
A warm “handover” process was established in order to provide full context of the conversation taking place to a “live” agent whenever Amelia needed to escalate the query. Importantly, when a live agent joined the conversation, Amelia stayed engaged in order to observe the dialogue and learn what she should do in the future. Although she would subsequently put forward updates to the process followed based on what she had observed, an SME check point was put in place to allow the company to ensure that Amelia would only learn new steps that they had approved.
In order to roll Amelia into production, it will be necessary to provide Amelia with access to the company’s ERP systems where invoicing data is held so that she is able to retrieve the right answers and execute any next steps such as uploading a new invoice. Based on the testing phase, Amelia’s successful resolution potential was estimated at 72% with less than 8 weeks of on the job training refinement.