AGI Framework

Cognitive and Psychological functional architecture

We would like to tell you a little bit more about our Artificial General Intelligent engine Framework which is at the heart of our software products.

An Artificial General Intelligent solution should be able to solve problems, make decisions and reason even if data are missing, even if, within a specific context, the current situation is not perfect or not well defined, it should be able to understand what is going on, it should be able to take care of your needs, your motivations and satisfy you by adapting itself to the context and to what really matters to you.

Linking together all mental activities and cognitive processes that humans have, we created a functional architecture which we enhanced by adding core psychological features such as needs, judgment, satisfaction, motivation and attitudes, making sure that information is processed by machines in a natural way.


In order to process the information in a human way (natural way), the foundation of our Artificial General Intelligent software architecture is as close as possible to how the biological neuron is processing information.

The cerebral cortex has several different “zones” which are involved in different cognitive and behavioral functions such as memory, cognition or thoughts.

Those functions communicate together so that the brain can process stimuli received by sensory receptors, extract information about the structure of the environment and process information with a set of rules, being able when necessary, to adapt response patterns.

We started from there and designed our Smart Neuron Component Architecture to be able to support core cognitive or psychological processes.

Smart Neurons have three functional parts: the first is dedicated to process incoming data (Dendritic Processing Level), the second to execute specific rules (Soma Processing Level) or cognitive processes and the third (Synaptic Processing Level) is in charge of sending the processed information to the receiving Smart Neurons.

We added at the dendritic and synaptic processing level an analogical data processing unit so that these communication channels are processing data like humans are processing those transmissions.

The heart of the Smart Neuron component (Soma Processing Level) is made of different functional parts dedicated to support the execution of one function and has a direct access to the long-term memory (VirtualBrains). This complex internal rule engine can be compared to a problem space where you typically find many possible impasses or paths and where cognitive processing can be used.


The world is perceived by our senses. Relevant information (stimuli) is acquired and classified into a structure made of objects classes. This process is called categorization.

This structure is made of symbolic classes. You have 3 types of classes: the object, his prototype and his abstraction (example: Woodpecker, Bird, Animal). Each class contains information stored in properties such as functional properties and descriptive properties, enriched with their related semantic fields. For a given class, his hyponym is a child class which does inherit of all the properties of the parent class. For a given class, a superordinate is a parent class which holds all the common properties. Once stored (in the long-term memory) in categories, knowledge can be represented, can be used when reasoning, making decisions and solving problems.

We have called this categorized structure the VirtualBrain, a data file containing all the information, all the properties and all the needed relations between these objects classes defining your business context.

We have a dedicated workbench to create VirtualBrains. From your given business context, we will build a specific VirtualBrain for your use case which will then be used by our Artificial General Intelligent engines.