One of Poste Italiane's main touchpoints through which it could offer assistance to its customers was the virtual assistant 'Poste'. This powerful tool required a lot of human effort to be maintained: the learning process on the sentences not understood by the assistant was completely manual and many of them were not even analysed due to the huge amount of data coming from different channels where the chatbot was installed.
A further complication was that the task was not scalable: if they wanted to deploy the virtual assistant on new channels, this would have meant an exponential increase in the number of incomprehensible sentences to be analysed manually, and consequently a huge expenditure of man-hours and costs.
The most interesting projects in NLP are those with a large amount of content and a lot of interaction with end customers: Poste Italiane was a perfect case for us because of these characteristics. The abundance of data is usually positive in the world of Ai, but only if it is structured in the right way and monitored efficiently. This project was aimed at working on these two aspects, creating an incredible mixture of Ai and people by exploiting what in jargon is called "human-in-the-loop"!
Among Poste Italiane's values, customer satisfaction and innovation are two cardinal points to offer an effective and efficient support service, which is why Poste Italiane chose to work with Indigo.ai to ensure that its virtual assistant would achieve the best possible performance, automating the learning process through the use of Indigo.ai's proprietary platform while reducing the human effort of managing and maintaining the chatbot.
The project was fully managed through Indigo.ai's proprietary platform and consisted of three phases: organising the bot's knowledge base, improving the self-learning process and analysing the service quality comments left by customers at the end of the conversation. During the first phase, Indigo.ai was able to use algorithms to optimally restructure the bot's knowledge base (brain), leading to a 10% increase in the understanding of customer requests. The second phase automatically qualified and clustered the previously incomprehensible requests, resulting in a tool that reduced human effort in training and maintaining the tool by 70%. In the third phase, customer feedback on the quality of the service was analysed, giving Poste Italiane's team additional insights on how to optimise the bot's knowledge in order to meet their customers' needs as much as possible.
Increased understanding of customer requests by the bot
Reduction of human effort (FTE) on bot maintenance activities
Happiness rate of operators for maintenance
Experience the power of Conversational AI and unlock the hidden value in your data. We walk you every step of the way to the adoption of AI in your company.
