Our responsibility to protect your data privacy is always our first priority. This article sets out which tools we use to deliver our conversational analytics, and how we maintain your data privacy during that process.


inmydata copilot uses the Microsoft Azure OpenAI API under the hood to deliver conversational analytics. We never send to Azure more than the first 5 rows of the relevant data required to answer the question. The models we use through Azure are stateless: no prompts, responses or data we provide are stored in the model. Additionally, prompts, responses and your data are not used to train, retrain, or improve the base models. Processing of the full data required to respond to the question is only ever conducted on our platform (hosted on AWS), and not shared with any other third party (that includes Microsoft Azure). The sample 5 rows are used to prompt the LLM to generate code that is executed against your data within our  own secure platform to answer to your questions.

 

Your questions and data:

  • are NOT available to any 3rd parties.
  • are NOT available to OpenAI.
  • are NOT used to improve OpenAI models.
  • are NOT used to improve any Microsoft or 3rd party products or services.
  • are NOT used for automatically improving Azure OpenAI models for your use in your resource

 

The Azure OpenAI Service is fully controlled by Microsoft; Microsoft hosts the OpenAI models in Microsoft’s Azure environment and the Service does NOT interact with any services operated by OpenAI (e.g. ChatGPT, or the OpenAI API).

 

The Microsoft Azure OpenAI privacy statement is available here:

https://learn.microsoft.com/en-us/legal/cognitive-services/openai/data-privacy