We make things simple
We simplify complex problems using our AI Engine called ADIN™ breaks down complex problems into simpler pieces - a ‘Divide and Conquer’ approach.
Echo’s award-winning AI Engine uses Autonomous Agents in an Intelligent System. Complex problems are broken down into simpler pieces called ‘agents’. Agents work independently, solving their own piece of larger problems. We publish our research in leading technical journals and present at leading Future Technology conferences.
What types of problems are solved?
Echo’s Business Automation product line solves problems of automating complex workflows common to service industry SMBs. Automated communication and process workflows are paired with agents which automatically respond to triggering information based on time, date, data, lat/lon/altitude geolocation or any combination of these items.
How is Echo AI software different?
Our Business Automation product line solves problems of automating customized workflows common to SMBs that are not solved by systems like Salesforce, Microsoft Dynamics, NetSuite or SAP. Also, there are many emerging online systems to help automate service industry SMBs but they don’t provide customizations. Competing systems solve basic tasks, but cause more problems by providing an incomplete solution.
An agent is an autonomous program which adapts itself to provide the most efficient way to accomplish any number of tasks involving communication, data transfer, business in applications Echo Messaging Systems creates compatible interchangeable agents that accomplish tasks that respond to Events, Devices, Timers, Locations, and more.
ADIN Cells recombine and reconfigure from a library of agents, to solve larger and more complex problems creating more robust software faster, using few resources.
Agents are two main components:
Triggering Criteria - must be true for the actions to run. Criteria can be based on time, data records, location or any combination. Ex. daily at midnight, when a new customer record is created, when a GPS-enabled device is detected in a geo-fenced area.
Action Responses - the set of actions performed when the triggering criteria is met. Ex. notify via email, push, and/or text, update a record status, copy a record in an different system, modify an agent parameter value to change how it runs, clone an agent with modified parameters.
ADIN has a REST API that allows developers to programmatically create ADIN Cells, and configure Agents' triggering criteria and action responses. The ADIN UI shows all ADIN cells and allows users to view their agents. Health Agents automatically monitor agents and notify administrators if they stop functioning. Container Technology, such as Docker, is used to manage scaling to thousands of agents.
More information on agent-based technology and programming are given in the research papers listed below.
Quantum Computing in Agent-Based Technologies
Agent-based solutions reduce complex applications into manageable components that run independently of each other. Quantum computing solves particularly difficult problems, such as Constraint Satisfaction Problems, that are time consuming on classical computers. Segmenting a complex problem into quantum and non-quantum components is well-suited to agent-based processing since the framework is already in place to simplify and solve through a divide-and-conquer approach. In this paper, we show how Quantum Agents in an agent-based intelligent system can be an ideal interface to quantum computing for solving many common and difficult to solve real-world problems. Quantum computing is being used for today's applications for optimization, resource allocation, scheduling and route calculations. Pairing quantum computing's advantages with the flexibility, integrity, and reusability of an agent-based system, produces application solutions quickly, that are reliable and evolve to meet expanding needs and growing scale.
Containerized Autonomous Agents for Cognitive and IoT Applications
Multi-agent autonomous systems solve many problems by organizing processing actions around triggering events. Agents working independently of one another, target their own specific criteria based on data, time, location or any combination of these. Responses to triggered events result in new or updated data, notifications or actions upon processes. Virtualizing the processing environment of agents decouples computing requirements and resources from specific agent functions to provide better resource management, expanded agent actions, and more sophisticated adaptation algorithms, included those based on machine leaning (ML) and deep learning (DL). Applications based on containerized autonomous agents where ML and DL based adaptations, and computing resources managed by container orchestration, are more dynamic, responsive and adaptive, where agents can number in the tens or hundreds of thousands or more. Structured data from unstructured data sources are the basis for cognitive and Internet of Things (IoT) applications. Intelligent systems with containerized autonomous agents are well suited to these types of applications. This paper describes the theory and applied real-world use of containerized autonomous agents in intelligent systems.
Anomaly Detection and Intelligent Notification
Applications and Operating Systems are programs responding to stimuli to perform tasks on computers, and these programs can be constructed in ways to minimize overall complexity of the software lifecycle, by organizing tasks into units that bring about a response and adaptation to stimuli. The response is the task's main function, the stimuli are user interaction, data source conditions, or time-based events, and adaptation is an opportunity for the task to adapt to its environment. Developing software using autonomous adaptive agents in an intelligent system minimizes overall complexity by organizing computing into reusable, scalable logical units that are by nature parallelizable. Each autonomous agent has a common core of virus resistant outer virtual casing by continually comparing its core attributes against master copies distributed via block-chain technology. Building upon research and implementation of these concepts of using intelligent systems using autonomous block-chain protected agents to rapidly create commercial-grade software over a wide variety of domains, we discuss in this paper how these concepts not only facilitate application development but can also be used for operating systems.
IoT Applications in an Adaptive Intelligent System with Responsive Anomaly Detection
Components to a robust, secure, reliable and dynamic platform for the Internet of Things includes anticipating for change, and preparing for the unexpected. IoT intends to deliver the next wave of disruption and growth to every facet of digital life, and now is the time for laying the groundwork, upon which IoT processes can be built. In this paper, we present the culmination of over 15 years of Artificial Intelligence research, software development and deployment of commercial applications built using adaptive software agents in an intelligent system framework with automatic anomaly detection and notification. We have created a system of components that have allowed us to create complex applications quickly through the use and re-use of adaptive agents in an intelligent system for automation, communication, and control. To be secure and adaptive, agents were also created whose primary purpose is to monitor normal behavior and react when something out of the ordinary occurs. Reactions can include halting processes, starting up other processes, notifying humans, interacting with 3rd party systems, etc. Each agent includes its own security layer as part of the agent triggering mechanism, as well as the ability to communicate thru all digital channels including Push Notification. Push Notification allows for server-based communication to any number of IoT devices and does not rely upon SIM-based (phone, text messaging) nor IP-based (networking) communication channels.
Creating Complex Applications Via Self-Adapting Autonomous Agents in an Intelligent System Framework
In this paper, we present a process, developed over years of practical commercial use, where applications accomplishing a wide variety of complex tasks are created from a common framework, through the use, recombination and iterative refinement of autonomous agents in a Multi-Agent Intelligent System. Driven by a need to solve real-world problems, our focus is to make businesses run more efficiently in an increasingly complex world of systems and software that must work together seamlessly. By listening closely to our customers’ problems, we discovered points of commonality, as well as patterns of anomalies related to the flow of data through communication channels and data processing systems, include accounting, inventory, customer relationship management, scheduling systems and many more. We solved their problems through the creation of an Intelligent System, where we defined and implemented software agents that were highly configurable, responsive in real-time and useable in various settings. Autonomous agents adhere to a standard format of three major components: the goal or triggering criteria, the action, and the adaptation response. Agents run within a common Intelligent System framework and agent libraries provide a vast set of component behaviors to build applications from. Agents have one or more of the following component behaviors: sensory aware, geo-position aware, temporally aware, API aware, device aware, and many more. Additionally, there are manager-level agents whose goal is to keep the overall system in balance, through dynamic resource allocation on a system level. To prove the viability of this process, we present a variety of applications representing wide ranging behaviors, many with overlapping agents, created via this approach, all of which are in active commercial use. Finally, we discuss future enhancements toward self-organization, where end users express their requirements declaratively to solve larger business needs, resulting in the automatic instantiation of a solution specific intelligent system.
Book: XML Design Handbook
The platform- and language-agnostic nature of XML makes it a natural choice for developers building cross-platform applications and is rapidly becoming the mechanism of choice for application designers who need to store and share data. Simply knowing the syntax and features of the language just isn't enough if you want to build powerful and efficient XML driven applications. You need to understand how to use the language and its features in the most effective manner. This is where this book comes in - assuming familiarity with the mechanics of XML, it analyzes all of the critical pieces of the XML space that require careful design in order to build efficient, robust, and extensible applications.
White Papers & Executive Summaries
Executive Summary: ADIN Quantum Interfaces
ADIN Cluster, Unstructured Data, Bias Agents and Quantum Agents