Frequently asked questions
The uses of chatGPT and Agora are complementary. chatGPT is primarily used to exploit a knowledge base, while for companies the knowledge resides in their applications/databases. We use chatGPT to simplify Agora’s configuration (NLP) and to handle specific use cases such as RAG. In addition, Agora is RGPD compliant and has a trusted AI.
The Agora solution comes preconfigured, with many “intentions” available. A specialized “no-code” workshop enables you to upgrade the solution quickly, and without any knowledge of automatic language processing. What’s more, we accompany your project, transferring skills and providing the necessary support.
Unlike a chatbot, we’re not an intelligent assistant, and we don’t pretend to be human.
Agora’s conversational interface is specialized to the application to which it is connected (yours).
Our job is to provide an application interface in natural language, enabling users to make requests and place orders, in several languages and on several channels, while remaining within a precise application context.
Most often, our model is an annual subscription based essentially on the number of users.
The price is degressive, from €1.2/month to around 30 cents/month, depending on the number of users.
Our customers are software publishers, and sometimes the number of users is not the factor that determines the size of their offer. In this case, we agree on a price based on their factor (number of files, accounting documents, customers, etc.).
The aim of no-code automation is to give process control to business experts, without requiring them to master software development techniques. This means they can concentrate on defining, fine-tuning and maintaining the processes for which they are the experts, without having to rely on software specialists, who are themselves often busy with other tasks within R&D.
To achieve this, no-code solutions offer simple, intuitive interfaces, describing the logic to be implemented: intent to be addressed, learning phrases, integration of variables, and so on.
The difficulties raised by the lack of interoperability within information systems are of two kinds:
- The ever-increasing variety of systems, devices, applications to be made to work together, each having its own interface (API) with its own formats, commands, parameters…
- The fracture between digital systems and their users: each solution has its own graphical interface, its dashboard, its dedicated application… The number of applications to load on a smartphone becomes excessive and often complicates the work of users.
To make all these elements interoperate, it is necessary to have a common language that is rich, scalable and durable. A first solution would be to define a posteriori this universal language; this is what many standardization bodies, manufacturers’ groups, etc. are working on.
Agora proposes another way: to generalize the use of the natural language, the one that humans have collectively defined and developed. Indeed this one presents many favorable characteristics:
- Rich, it allows to place commands (“open the door”) and to make requests (“what is the CO2 level?”);
- Flexible, it adapts easily to new situations (if you can do it, then you can say it);
- Intuitive, it allows many modes of expression: learning a language consists in mastering the rules of assembling words, not in learning “by heart” all the possible sentences (in almost infinite number);
- Natural, it reduces the gap between technical solutions and their users;
- Durable thanks to its fluidity, it is not about to go out of fashion, and its lifespan will be far superior to all technical standards and conventions;
- Common, it is the property of all and belongs to no one.
This is one of the fields of artificial intelligence, which involves programming a machine to learn how to perform tasks by studying examples.
To benefit from the advantages of natural language and make digital systems interoperable, a number of technological challenges must be overcome. Agora’s NLP is the result of several years of research, conducted by our teams with the help of international specialists, and has been the subject of an academic publication. Its properties allow it to address the most constrained operational environments:
- High precision to cope with the ambiguities inherent to natural language, thanks to a contextual implementation;
- Deterministic, for high operational safety;
- Ultra-fast (a few milli-seconds);
- Lightweight, it can be integrated into edge functions, gateways and devices with Raspberry Pi-like computing resources
- Flexible, it is easily adaptable to new actions (“intent”), attributes, etc. and allows the easy handling of particular cases (jargons…);
- Multi-language, it detects the user’s language and facilitates interactions in international environments.
Our solution is hosted in the cloud, at three different providers with load balancing and automatic reconfiguration in case of failure, to guarantee you permanent access.
We adapt to your governance, management and architecture. Whether you have your own in-house storage device or need to feed a storage system/data warehouse, we can direct the data collected/captured via our platform.
To date and for example we support French, English, German, Italian, Japanese, Portuguese, Russian, Spanish, Vietnamese, Polish…
And we know how to make the necessary adaptations for any new language you may need.
Agora Software will develop and integrate the interface with your application (connector) into its platform.
The development cost is estimated by Agora at the start of the project and generally corresponds to a few days’ work.
We are a conversational AI editor for editors. Our customers are publishers of business applications (HRIS, Finance, ERP, resource reservation, etc.) with whom we integrate on a white label basis.
We also work with the innovation and digital departments of many local authorities.
The ‘edge’ mode allows you to deport your connector within your infrastructure, while enabling global control from the cloud. You provide the server, we provide the Docker container and connector.
Our solution is particularly agile and easy to integrate into your product. It has been specifically designed to meet the requirements and constraints of a software publisher.
What’s more, we have our own technology (sovereign and explainable AI), with an implementation insisting on RGPD and security aspects (separation of projects).Accordion content
We disappear completely from the eyes of your users. On the other hand, we fundamentally believe that you have everything to gain by making your application available where your users are.
What we propose is to integrate a conversation interface into your application. Your users will be able to access it directly from :
- A chat window directly integrated into your application (online or mobile)
- MS Team, Slack, Google if your users are regularly connected to professional messaging systems
- WhatsApp or Messenger if this is relevant for non-equipped profiles.
Less effort and a multiplication of access modes reinforce your users’ usage and adoption.
Agora is based on the principle of reusing existing communication applications. If they support voice, great. If they don’t, we’ll propose a Voice-to-Text function if it’s relevant to your users.
During the integration phase, we work with you to define the most appropriate interactions for your users, because there are many different ways of interacting. And it’s true that a conversation can seem long if several variables have to be collected.
Typically in this case, in addition to dialogs, we implement ‘templates’ or cards that can be completed like a form, respecting the context input rules (why not for a purchase order) and your graphic charter.
The advantage of these forms is that they appear at the user’s request: I want to create a new order? Create me a copy of order no. 123?
No more barriers to using your application!
Do you have another question?
You’ll find a wealth of additional information on this site, including details of the Agora Software solution, usecase examples and blog posts on AI and the ecosystem.
We hope you find these FAQs useful. We’ll be adding to them as we discuss them with you.
We’ll be happy to answer any questions you may have and advise you on the best way to make your applications conversational. We look forward to hearing from you!