Personalized AI Assistants
Personalized AI models for individuals, organizations and communities are able to address user needs better than general models. Previously, we would need to perform difficult and time-consuming training of AI models on our own data for a particular use case. However, this is no longer the case with modern AI models, which are very good a multitasking or learning tasks given only a few examples. This is achieved by simply adding information to the input prompt. This can include the task that you would like the model perform (e.g. summarization, question answering), some examples of inputs and outputs that you desire, or some data or context that the model can use to create the output.
Users of ChatGPT may have found that passing more context in the prompt tends to create better outputs. For example, if you ask ChatGPT to write an email to a prospective employer, you may have given it some context about previous correspondences and your resumé. Manually copying and pasting from our personal data sources into the input prompt every time is tedious. What if we could automatically retrieve relevant context from our personal data sources (based on details of the prompt such as the requested task), and feed this data to ChatGPT? Asking ChatGPT to find you a job could automatically pull in previous emails that are relevant, as well as information from your resumé.
This is the aim of the Algovera Flow platform, which allows you to connect your data sources (such as Discord, Notion, Obsidian, GitHub, Calendar, Twitter and YouTube) that can be used dynamically retrieve relevant data, based on the requested task. This data is used with the AI model to create personalized AI assistants like ChatGPT that help to complete various tasks in your everyday workflows.
Last modified 7mo ago