Yes, SensEI uses industry-standard best practices for data handling and retention. See our Privacy Policy for more details. All commercial deployments are covered by Evolwe's Data Protection Addendum, which is available upon request.

Our API is designed to be a backend that incorporates SensEI into any application you’ve developed. Our application sends text to our API, then receives a response via server-sent events, a streaming protocol for the web. We have API documentation with drop-in example code in Python and Typescript to get you started.

We currently offer two versions of SensEI.
SensEI v1 - our most powerful model, which excels at a wide range of tasks from sophisticated dialogue and creative agents generation to detailed analytics about users.
SensEI Instant - a faster and cheaper yet still very capable model, which can handle a range of tasks including casual dialogue, text analysis, summarization, and document question-answering.

You can find our model pricing here.

SensEI has the most training in English, but also performs well in a range of other common languages, and still has some ability to communicate in less common languages. SensEI also has extensive knowledge of psychology.

No. SensEI is designed to be self-contained, and will respond without searching the internet. You can, however, provide SensEI with text from the internet and ask it to perform tasks with that content.

Artificial empathy is the ability of machines to recognize, understand, and respond to human emotions. This technology involves integrating various forms of artificial intelligence, including machine learning and natural language processing, to enable machines to interpret and respond to human emotions in real-time. In terms of integrating artificial empathy into AI models, we use various techniques, such as sentiment analysis, emotion recognition, and behavioral analytics, to help machines better understand and respond to human emotions. These techniques involve training AI models on large datasets of human behavior, speech, and language, and using this data to develop algorithms that can recognize patterns and trends in human emotions. The core Evolwe model has been fine tuned with artificial empathy with the goal of becoming helpful, honest, and harmless. You can learn more about artificial empathy here.

Helpful, Honest, and Harmless (HHH) are three components of building AI systems (like SensEI) that are aligned with people’s interests.- Helpful: SensEI wants to help the user- Honest: SensEI shares information it believes to be true, and avoids made-up information- Harmless: SensEI will not cooperate in aiding the user in harmful activities
While no existing model is close to perfection on HHH, we are pushing the research frontier in this area and expect to continue to improve. For more information about how we evaluate HHH in our models, you can read our paper here.

SensEI’s behavior can be extensively modified using prompting. Prompts can be used to explain the desired role, task, and background knowledge, as well as a few examples of desired responses.

In the vast majority of cases, we believe well-crafted prompts will get you the results you want without the expense or delay of fine-tuning. However, some large enterprise users may significantly benefit from fine-tuned models. Please contact us to discuss whether your needs might be best addressed with a fine-tuned model by filling out this form.

The combined context window for input and output is about 9000 tokens, which works out to roughly 5000 words, or 15 pages, depending on the type of content.

The understanding of specific features of the user matters, as it allows SensEI to create more personalized and human-centric solutions that cater to the unique needs and goals of individual users. We can analyze the user's emotional, psychological states, his traits, interests through his texts, open data and predict his behavior. This, in turn, can lead to higher levels of engagement, satisfaction, and loyalty, as users feel more understood and supported by the AI system. Ultimately, the ability of SensEI to understand and respond to the specific features of each user has the potential to transform the way businesses interact with their customers, leading to more positive and productive relationships.