AI security

This article describes how UI Bakery AI works in regards to maintaining data privacy and security principles.

Overview

  • UI Bakery AI only works with data that users already have access to

  • Client data is never used to train Large Language Models (LLMs)

  • Neither UI Bakery nor LLM providers store PII or client data

Introducing UI Bakery AI

UI Bakery AI accelerates your workflow to help you:

  • Generate production-ready applications with minimal effort

  • Debug failed actions with clear insights and error context

  • Receive smart code suggestions while building requests

  • Get help with technical questions using AI chat's documentation mode

You can read more about the AI features we offer in the following articlesπŸ‘‡

⭐Custom components 2.0✨AI Assistant

Behind the scenes

UI Bakery AI provides you with personalized code suggestions using third-party LLMs and the context from your app and organization. When you interact with the AI, it captures your prompt and certain app details (for example, components, data models, etc.) to generate a response. The LLMs then process this data and return suggestions. They don't store any of your information after processing.

Data privacy

UI Bakery AI is based on the Open AI GPT model and Claude AI. During your interactions with the AI, these models may have access to the following user data:

  • The question/prompt posed by the user or the code generation request

  • Details about the action currently selected, including its name

  • Information regarding the step presently selected within the action, such as:

    • Step name

    • Action code/SQL

    • Action type

    • Any errors resulting from the action

    • The structure of the result, including the key names and their corresponding types

  • Names of the components and other used variables

  • The payload sent to the data source (including data specified by the user)

  • Structure of selected database tables, including columns

Last updated

Was this helpful?