Google patents method for merging conflicting AI prompts
This patent describes a system that collects instructions from multiple sources, called agents, and combines them into a single request for an AI model. When the instructions disagree on specific details, the system uses a disambiguation process to pick one version over the other before sending the final prompt to the model.
In the filing’s own words
Implementations relate to: obtaining, from each agent of a plurality of agents, a respective natural language (NL) prompt, wherein each of the respective NL prompts includes one or more candidate parameters; aggregating the respective NL prompts to form a joint NL prompt; and causing the joint NL prompt to be processed using a generative model (GM) to generate responsive content. Aggregating the respective NL prompts to form the joint NL prompt can include: identifying a first candidate parameter and a conflicting second candidate parameter included in the respective NL prompts; selecting, based on a disambiguation process, the first candidate parameter for inclusion in the joint NL prompt in lieu of the conflicting second candidate parameter; and determining, based on the respective NL prompts and the selection of the first candidate parameter in lieu of the conflicting second candidate parameter, the joint NL prompt.
What exactly they claim (claim 1)
1. A method implemented by one or more processors, the method comprising: obtaining, from each agent of a plurality of agents, a respective natural language (NL) prompt, wherein each of the respective NL prompts comprises one or more candidate parameters; aggregating the respective NL prompts to form a joint NL prompt, wherein aggregating the respective NL prompts to form the joint NL prompt comprises: identifying a first candidate parameter and a conflicting second candidate parameter, wherein at least one of the respective NL prompts comprises the first candidate parameter and at least one of the respective NL prompts comprises the conflicting second candidate parameter; selecting, based on a disambiguation process, the first candidate parameter for inclusion in the joint NL prompt in lieu of the conflicting second candidate parameter; and determining, based on the respective NL prompts and the selection of the first candidate parameter for inclusion in the joint NL prompt in lieu of the conflicting second candidate parameter, the joint NL prompt; and causing the joint NL prompt to be processed using a generative model (GM) to generate responsive content.
Facts
- Company
- Google (GOOGLE LLC)
- Official title
- Collaborative framework for utilizing generative model(s)
- Patent number
- US12769956B2
- Application number
- 18962639
- Filed
- Nov 27, 2024
- Granted
- Oct 20, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06F 40/40 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 AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.