Amazon patents method to pick right tools for AI prompts

Amazon describes a system that helps large language models find the specific software tools they need to complete a task. It uses multiple methods, including searching descriptions and applying rules, to create a short list of the most useful components for the AI to use.

In the filing’s own words

Techniques for identifying components (e.g., application program interfaces (APIs)) relevant for a large language model (LLM) prompt are described. The shortlister includes one or more proposers that each select n components for performing an instant task. The n components from each proposer may be merged and reranked to produce a ranked list of K components for inclusion in the LLM prompt. The shortlister proposers can include, among others, a request-based proposer, query-based proposer, and/or rule-based proposer. In particular, the query-based proposer may utilize a LLM to generate a query to search component descriptions to identify n components the proposer determines are usable to perform the instant task.

Facts

Company

Amazon (Amazon Technologies, Inc.)

Official title

COMPONENT SHORTLISTING

Publication number

US20260331107A1

Application number

19647174

Filed

Apr 14, 2026

Published

Oct 22, 2026

Inventors

9

Claims

21

Classified under

More from Amazon in AI & software

• Amazon patents system that cites sources for AI answers Sep 29, 2026
• Amazon patents tech to swap words in movies using actor's voice Sep 8, 2026
• Amazon patents ML tool to add graphics to live sports from moving cameras Sep 15, 2026
• Amazon patents shopping assistant that remembers your search filters Oct 6, 2026
• Amazon patents system where AI agents split tasks and talk to each other Oct 20, 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.