Google patents tool that builds custom AI models from simple text inputs
Google describes a software interface where users can select an existing AI model and enter specific instructions along with example questions and answers. The system uses these examples to fine-tune the model and then generates code that allows the user to access this customized version through a standard software interface.
In the filing’s own words
A method includes receiving a request indication indicating a GUI interaction by a user on a user device, and in response, providing to the device a response configured to cause the device to display, within a GUI, a structured prompt including a plurality of user input fields, each user input field representing a corresponding training sample and including a first corresponding text input field for capturing input text to be provided to an ML model, and a second corresponding text input field for capturing ground-truth output text. The method also includes receiving, from the device, the training samples, and, in response, adjusting the ML model using the training samples. The method further includes receiving, from the device, test input text, generating, using the adjusted ML model, test output text based on the test input text, and providing, to the user device, the test output text for display within the GUI.
What exactly they claim (claim 1)
1. A computer-implemented method executed by data processing hardware that causes the data processing hardware to perform operations comprising: receiving, from a user device, a request indication indicating a graphical user interface (GUI) interaction by a user within a GUI presented on the user device; based on the request indication, providing, to the user device, a structured prompt response configured to cause the user device to display, within the GUI, a structured prompt comprising: a model selection input element allowing selection of a pre-trained machine learning (ML) model from a plurality of different ML models; a preamble text input field for capturing text identifying instructions for the selected pre-trained ML model; and one or more user input fields representing a corresponding training sample, the one or more user input fields comprising a first text input field for capturing example input text and a second text input field for capturing corresponding example output text; receiving, from the user device, a selection of the pre-trained ML model, the text identifying instructions, and one or more training samples; adjusting the pre-trained ML model using the text identifying instructions and the one or more training samples; generating computer code configured to call an application programming interface (API), the API configured to provide access to the adjusted pre-trained ML model; and providing the generated computer code to the user device.
Facts
- Company
- Google (Google LLC)
- Official title
- Integrated Development Environments for Generating Machine Learning Models
- Publication number
- US20260359023A1
- Application number
- 19745569
- Filed
- Jul 17, 2026
- Published
- Nov 12, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06F 8/35 Physics & computingG06F 3/0484 Physics & computingG06F 8/34 Physics & computingG06F 11/3698 Physics & computingG06N 3/0455 Physics & computingG06N 3/096 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents method for LLMs to self-correct and learn from mistakes Oct 27, 2026
- Google patents search results that mix real clips with AI-made video Nov 10, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.
