Since our founding in 2016, we have been part of the unprecedented transformation in the world of bots and virtual assistants. We work to transform them into fundamental tools in the digital era, to improve the interaction between brands and their users, and we enhance their power as allies of organizations to reduce costs.
Recently, we revamped our narrative to clearly present our evolution and that of our technology. To achieve this, we have adopted the concept of "generations" as our main focus, reflecting the path we have taken from the first rule-based bots to sophisticated artificial intelligences (AI) capable of emulating human behavior.
First generation: rule-based bots
These bots are the pioneers and operate with a predefined set of rules. Their interactions are limited: they cannot handle queries outside their initial programming, which means that they do not learn or adapt over time. Their interfaces are simple and based on option menus. They integrate with corporate information systems.
Some of the typical functionalities of bots of this generation are:
- Customer service for frequently asked questions.
- Help for navigation in corporate sites.
- For utilities, notification of due dates, management of utility payments, schedules and availability.
- For online stores, sending abandoned cart messages, customer status change, sale completed and other events.
- Sending promotional messages and surveys via WhatsApp and other channels.
They are still in place and are sufficient for many organizations. Often, they function as the gateway to this world before evolving over time.
Second generation: hybrid (tree + basic AI)
Moving towards more fluid interaction, this generation combines basic rules with AI elements. Platforms such as Dialogflow and Watson enable these bots to handle more complex conversations and detect intent from keywords. These bots can receive images or voice messages and extract information from their content.
Second generation bots help to:
- Prequalify leads in sales.
- Receive voice claims reports from insurance companies (e.g., a customer sends an audio report of what happened).
- Manage the catalog and search for items by replicating online stores on WhatsApp.
- Answer queries on an assigned document base (PDF, websites, Excel, among others).
Third generation: conversational (non-generative AI)
Driven by deep learning, these chatbots can detect sentiment, interpret natural language and handle complex interactions without the need for a predefined structure. They can relate information from multiple databases and communication channels.
They are able to understand and remember context autonomously, as well as predict behaviors and needs. However, their responses are predefined as they cannot generate text.
Some of the new features of this generation are:
- IT support that solves problems based on previous cases and current context.
- In the healthcare sector, appointment management that takes into account the patient's history and preferences.
- Personalized shopping advice that remembers sizes and style preferences to suggest clothes.
- Bots that, based on the image of a gondola, determine replenishment needs and manage orders.
- Management of travel bookings involving complex queries.
Fourth generation: generative virtual assistants
These bots are based on generative AI to offer even richer and more human-like interactions. They are capable of performing complex tasks and advanced learning, placing them at the forefront of chatbot and virtual assistant technology.
They know each user and have unique chats based on their past preferences. In addition, the personality with which the bot responds can be defined: from language and tone of voice to imitating a character. They are trained to work with and process large volumes of data; for example, formulating responses from all the information on an intranet.
These are some of its most surprising uses:
- Manage and resolve technical support incidents (identify and alert the user).
- Autonomously manage agendas and e-mails, prioritizing tasks.
- To serve customers both to resolve their queries and to anticipate their future needs.
- For industry, support systems that schedule maintenance based on predictive failure analysis.
- Urban planning that optimizes projects based on simulation and data analysis.
- Analysis of judicial dispositions and subsequent actions, such as freezing or unblocking of bank accounts according to resolution.
