The mission of Deepdesk is to improve customer service with smart technology. Our AI empowers agents with autocomplete and reply suggestions. Those suggestions are based on millions of conversations with customers. However, agents still want their conversations with customers to be personal in tone-of-voice. So, we worked on personalization of our AI. The results exceeded our expectations.
The best possible answer
We do big data. Our neural networks are trained with data from contact centers. Over a million conversations have been uploaded to our servers, for us to find the best possible answers. Our autocomplete and reply suggestions have boosted quality and standardized conversations. All this much to the satisfaction of both agents and customers.
What humans do best
But we also strongly believe in real human interaction. That is why we did not build a chatbot. We built something better: AI that supports the human agent. The AI suggests, the agent decides. We save the agent time-consuming searches and redundant typing, allowing him to do what humans still do best: feeling what the customer needs and dealing with emotions and outside-the-box requests.
Request for personalization
In a research study we asked over 100 agents of one of our clients how they wanted to improve Deepdesk. Though they were happy with our solution, some agents wanted our autocomplete and reply suggestions to reflect their personal style more.
Here is the thing: if the answers the AI suggests are too generic, the agent might not feel at ease with the suggestions. One agent might say: ‘‘Hi, how can I help you’ another agent will say; ‘Goodmorning, what can I do for you?’’ We may only want to recommend the phrase that suits the specific agent.
Making AI more personal
Since it is our mission to assist agents in writing text as easily as possible, we adjusted the algorithms, with our AI giving more weight to the given answers by the agent in question. We compared our new models in an A/B test.
Indeed, the new model with improved personalization was chosen more often, so we made the adaptation for all agents.
Encouraged by the results of personalizations, we added another feature for one of our customers: Personal Collection. The agent can now manage all his or her own standard responses, giving even more sense of control (More on Personal Collection later).
This time, when we released our updated version, something amazing happened. Agents started to use Deepdesk more. A lot more.
The chart below shows the use of Deepdesk by agents both in absolute terms (blue columns) and expressed as percentage (white line). We released our new version at the end of December. We saw a rapid increase in use:
We are excited over the results of course. Clearly, having a sense of control and personal influence does motivate agents to use Deepdesk more. Since we are working with humans, in hindsight, that should not have come as a surprise.