ONDEWO Artificial Intelligence Management (AIM) Platform

This platform lets you manage all your AI projects, giving you full control over what it does.

Easily design your own dialogue
Test the AI on the platform before it goes live via chat or voice
Review the past interactions of the AI

Benefits

What you gain

ONDEWO Artificial Intelligence Management (AIM) Platform is so easy and exciting to use for both: non-tech savvy users and data scientists. A person with no IT background can easily create and maintain exceptional conversational experiences and automations without any headaches by the guides offered within the software. A data scientist can drill down deep into technology and can configure each algorithm used in great detail.

Easy to use

The interface is intuitive, making it easy to work on it. It also comes with a guide to make it accessible to everyone without excessive introduction courses, so that people who do not have a technology background can use it.

Choose your language

You can choose the languages that your AI interacts in with the customer. The available options expand, as new languages and dialects will get added continuously.

Full control over projects, users and permissions

The platform gives you the ability to build, train and optimize your own AI for your specific use case without needing a professional for it.

Demo

Try it out for free!

Have a look around our system to get a feeling of how it works.

01

Show multi-project overview and select example project

02

List entities and add a new synonym to an entity

03

List intents, open intent and add a new training phrase

04

Test your conversational AI agent

Important Features

What makes it special

Administrate projects and users

We have four algorithms that can get trained. The more algorithms run, the more the AI learns and understands. That enables it to complete more difficult tasks after a few interactions.

Model simple FAQ-like and complex multi-turn, context aware conversations

The entities can be created by hand according to the specific application. An AI can generate new entities by the algorithm itself, which only need to be confirmed by a responsible employee with a few clicks.

Create and maintain entities and synonyms with AI support

We have four algorithms that can get trained. The more algorithms run, the more the AI learns and understands. That enables it to complete more difficult tasks after a few interactions.

Create and maintain intents and training phrases with AI support

We have four algorithms that can get trained. The more algorithms run, the more the AI learns and understands. That enables it to complete more difficult tasks after a few interactions.

Live testing for voice assistants and chatbots

The built-in voice assistant and chatbot is used to test conversations during design phase or review existing customer conversations with the AI agent. If an error is spotted, the user can interactively correct wrongly detected entities and intents as well as modifying responses on the fly.

Session reviews and analytics

Get an overview of all conversation sessions between a human and an AI agent and analyze the quality of the conversation and provide feedback to the AI to improve the conversational experience. Various filtering possibilities are available ranging from detected intents or entities, confidence intervals, time and date etc. Our AI even labels the conversations a human should take a closer look at to check how it can be improved.

Built-in voice assistant and chatbot for deployment

Do you have a website or a mobile app? You can easily deploy your ONDEWO AI agent on your website or mobile app by copying and pasting some snipped.

Webhook capability

A connection between the AI and another service or a database can be easily established to provide more context to the AI agent for a better and more lively conversation with a human. E.g. , it can enable the search for customer-specific data to personalize the call with a greeting or can check the medical data based on given social security number.

Self-service AI algorithm optimization (Data Scientist feature)

Over 20 cutting-edge AI algorithms from the research areas of natural language processing, machine learning and deep learning are configurable in great detail throughout the AIM platform (e.g. learning rate, pre-trained model, transformer algorithm types, pre-processing techniques, meta-learning etc.). Data Scientist have a “no-code” platform to optimize the algorithms for the training to achieve the best possible customer experience. Training these algorithms fully distributed across multiple GPU-servers is just a click on the “train” button.

On-premise and cloud hosting

All features are available on both versions. The on-premise solution easily installs on all operating systems with standard Docker deployment environment on your own IT Infrastructure. Furthermore, it allows for a higher degree of data protection and control. With the cloud option, there is no maintenance needed as it gets provided by ONDEWO. The cloud option is billed on a usage basis.

News

What else is new

Register here for the ONDEWO newsletter. You will be up to date, and you will always be the first to know about new products and solutions as well as other news.