Welcome to a solution that understands both people and data.
A solution that lets anyone search, process and connect information by meaning instead of keywords.
A solution that performs better than the most famous search engines AND is applicable directly to your organization's own data and documents. With industrial strength, full scalability and start-of-the-art security.
Data used to be a problem. Now it's a source of profit, performance and customer satisfaction.
Discover how and why adopting SensibleData is the most sensible business decision you can make.
Exponential growth, rising costs, lifecycles, silos, security, compliance...
While traditional, keywords-based solutions can't cope, SensibleData delivers field-tested solutions.
Problems solved: Enedis, France's main power grid operator, wanted to be able to predict intervention times for their field technicians, taking into account a huge history of incident reports as well as public traffic and wheater data, with possible alternatives. The application adapts to the company's functional organization by regions and the precise predictions vary according to an infinity of incident conditions details: site layout and history, types of equipments, time of day, etc. The predictions are available in real time, with as few keystrokes / vocal inputs as possible. AI-based autocompletion everywhere enables call centers' respondents to give estimates immediately upon incident reports.
Data types: The intervention history mainly consists of Excel files summing up intervention reports. Routes, traffic and wheater conditions come from public data served by backends dedicated to the application. None of the original documents had to be modified or otherwise prepared beforehand.
Problems solved: Enedis, France's main power grid operator, needed a search / data matching engine capable of answering very technical questions and detailing corporate processes from a significant documents base (Office and PDF files, mainly). The SensibleData solution was delivered with two user interfaces : one is a conversational chatbot, the other is a more classical search engine except that it features a number of user-definable parameters (see the sidebar) to fine-tune results. Both implementations are operational as delivered, with backends and data residing on premises. Both implementations support vocal input so that techniciens in the field can get results hands-free.
Data types: The source knowledge base is a compilation of technical documents repositories covering all aspects of Enedis' internal procedures including field interventions, hardware information, security guidelines and HR-related processes. None of the original documents had to be modified or otherwise prepared beforehand.
Problems solved - Total S.A., one of the six "Supermajor" oil companies in the world, has a very strong commitment to health, security and environment (HSE) matters. To raise awareness and share internal + regulated best practices among employees, they needed to expose and facilitate access to their global treasury of HSE resources. Smarty, based solely on SensibleData, was the solution: a multi-purpose bot capable of answering any HSE-related question, text or speech. Smarty is shown here in its English user interface, with a question asked in English returning results in the currently available languages (SensibleData being meaning-based, the source language has no importance).
Data types - The exposed HSE resources include Office files, PDFs, corporate intranets and public websites contents, in several languages. The tables shown in the screenshot are rendered from a PDF table. None of the original documents had to be modified or otherwise prepared beforehand.
Problems solved - Société Générale, a leading global 'universal' bank, faces complex compliance regulations on most of its operations. To the extent that, even for the most seasoned professional, knowing everything within their domain is just impossible. For SensibleData, the objective is simple: to help everyone find the right, actionable information as if they could ask a team of experts available 24/7 in all timezones. Since regulations may vary territory-wise, this usecase returns relevant results whatever the language of the question and that of the target documents. The screenshot shows results in English and French to a question in English, with SensibleData's result evaluation widget enabled.
Data types - The compliance resources included in this usecase consist of an intranet with explicative pages leading to regulatory PDF documents, either public or of SocGen origin. None of the original documents had to be modified or otherwise prepared beforehand.
Problems solved - Service-Public.fr is the global portal of the French public administration. It exposes a comprehensive collection of information, resources, reference texts and official forms relating to legal and regulatory matters for individuals, businesses and non-profits. At the request of a major French insurance company wishing to offer their customers a 24/7 legal Q&A system, thereby saving millions a year in level-1 customer assistance, SensibleData is giving access to this immense wealth of knowledge via a natural-language conversational interface (to be integrated later within the company's website and mobile apps). The screenshot shows a sample question and its final answer plus the offical references and a number of machine-learnt suggestions that help users find more on the current topic.
Data types - Service-Public.fr is an open data website. Its entire content is just read, daily and automatically, for direct availability in SensibleData.
SensibleData's difference is that it delivers immediate, measurable benefits in data-related usecases.
Here are the main reasons why SensibleData means user satisfaction and sustainable value creation: