Customer service agents spend most of their time solving simple but repetitive customer queries. Our product is a tool that provides automatic, intelligent recommendations for macros, responses and other next actions for customer support agents. We integrate these recommendations into CRM and ticketing systems such as Zendesk. The product is more intelligent and effective than currently used automation alternatives, such as copy & paste templates or chatbots.
If you are facing a high volume of repetitive customer queries, the highly probable answer is yes! If you face challenges in optimising your support function, please reach out.
Our software supports European languages (we have successfully worked with English, Spanish, German, Italian, French and Finnish). If you are interested in using a particular language, please send an email to email@example.com with details.
We support all text-based channels, such as live chat, social media and emails.
We offer a 30 day free trial period for qualified customers on Zendesk - to get started, install our app. After the trial period, we charge a bespoke fee per seat or per used suggestion.
We are different in two main ways:
Our tool presents recommended macros, responses or other next actions to the agent.
A more common alternative would be to let the AI automatically send the response (chatbot). If the response created by the AI is not accurate, this would lead to a poor customer experience. By presenting recommendations to the agent, the human agent remains in charge.
We use a cutting-edge AI which is built on self-learning technology. We let the AI review your historic conversations. This way, it understands what a good answer and next action in any given situation is. The patterns learned from the initial training allow the software to generate relevant recommendations in future.
Self-learning is what we use at True AI. It enables us to learn automatically from past and ongoing conversations.
Partial machine learning is what is usually used to create modern “chatbots”. Chatbots use IF-THEN type rules ("IF the customer says X, THEN respond with Y"). More sophisticated bots use basic machine learning to be more flexible in recognising incoming queries.
Partial machine learning relies on explicitly programmed rules to understand how those parts are connected. It works well for extremely simple conversation (where there are only a few things that can be said or requested) but fails for more complex conversations.
As a result, partial machine learning systems are prohibitively expensive and inflexible, frequently leading to a poor user experience.
We follow strict security policies and best data safety practices, including but not limited to Microsoft Azure threat blocking, detection and logging services, Azure Web application firewall for detection and prevention of malicious requests, Azure DDOS protection, HTTPS encryption, storage encryption and anonymisation, OAuth2 authentication, Azure KeyVault storage, employee security and confidentiality training, security clearances and NDAs, professional indemnity as well as public liability insurance.
Our key integration is with Zendesk, but our roadmap also includes other systems. We also have a product API. If you don't use Zendesk or require a custom integration, let us know and we'll be happy to explore our options.
We have a product API. Please contact firstname.lastname@example.org for a demo.
Depending on the dataset we will need 10,000+ conversations to create an effective solution.
If you use Zendesk, the cost is 0. For custom integrations we charge a bespoke fee depending on how complex the integration procedure is.
After we have received the data, we will need between 5 - 15 days to prepare our AI solution by training the algorithm.
True AI Ltd. is co-funded by the Horizon 2020 programme of the European Union.
True AI Ltd. is registered in England & Wales, company no. 09864737. Registered address: 20 Ropemaker St, London, EC2Y 9AR, United Kingdom.