Product Updates: Intent Based Helpfulness Scoring, Customer Interaction Metrics, Chat Window Location Customization And More!

This is our monthly update highlighting recent improvements and new features in our product line.

 

  1. Detailed intent based helpfulness score from customers

Regular feedback from the customers is essential for every business. For deeper insight, it is important to analyze feedback for every topic that conversational AI handles. We do it by measuring helpfulness score. Helpfulness score by intent can be considered one of the most influential and essential key performance indicators for conversational AI’s. The binary nature of was it helpful? – yes or no – can provide quite harsh but accurate insights on customer satisfaction and on what could be improved upon. Bot trainers, developers and content creators can sort and rank topics on a selected time range either by subtopics, count of sessions, feedback requested, feedback provided, feedback positive or feedback negative. The data updates automatically and can be accessed by web browsers.

 

  1. Count of interactions with text; with buttons; with text and buttons

To gain insight on customers behavior and preferances when interacting with chatbots we have included a neat little way to monitor count of interactions either with text, with buttons or with both text and buttons. Some people prefer to use free text, others know exactly what they want and quickly navigate to the desired topic through clickable menu. Measuring customer behavior makes it possible to tailor pleasant user experience for every kind of customer.

 

  1. Add chat to multiple websites

To promote creativity, flexibility and efficient use of resources we have enabled adding chat windows to whole site or specific URLs. These chat windows can be backed by conversational AI, human agents or both. This allows to allocate resources (which in some cases may be limited) more efficiently and guide customers to specific sites.

  1. Customers can rate agents

Previously, we mentioned giving feedback to conversational AI based on overall helpfulness of the topics provided. In some cases, AI needs help from their fellow human colleagues. For agent managers and ultimately business owners, it is crucial to know your team strengths and weaknesses. One of the easiest ways to gather this kind of knowledge is to let customers give feedback on your agents work. After interacting with an agent, a customer can rate the agent on a 5 star rating scale, which will then adjust the overall average score for every agent.

  1. Archive search

Ever felt the need to go back to an individual case where a customer or the agent told something specific? With archive search it is possible. Users can pick the desired time range and search keywords from there. The search results can be filtered by Chat ID, username, user ID, agent ID, agents, tags, queues and URLs.

Leave a Comment

Subscribe to our newsletter for the latest in AI