US 12,461,955 B2
Integration flow generation using large language models
Hadi Minooei, San Francisco, CA (US); Yazdan Jamshidi, Winter Springs, FL (US); Yanqi Luo, San Francisco, CA (US); Santiago Bassani, Dublin (IR); Mofeyifoluwa Olaoluwa Oluwalana, San Francisco, CA (US); and Shobana Ranganathan, Palo Alto, CA (US)
Assigned to Salesforce, Inc., San Francisco, CA (US)
Filed by Salesforce, Inc., San Francisco, CA (US)
Filed on Dec. 5, 2023, as Appl. No. 18/530,026.
Claims priority of provisional application 63/537,434, filed on Sep. 8, 2023.
Prior Publication US 2025/0086212 A1, Mar. 13, 2025
Int. Cl. G06F 16/33 (2025.01); G06F 16/334 (2025.01); G06N 20/00 (2019.01)
CPC G06F 16/3344 (2019.01) [G06N 20/00 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A method for generating an integration flow with a large language model (LLM), comprising:
receiving, via a cloud-based platform, user input comprising a request for generation of the integration flow, the integration flow comprising code to interface, within a runtime environment, one or more processing elements with one or more input elements that provide data and with one or more output elements that accept a processed version of the data processed by the one or more processing elements;
generating a query based at least in part on the request and a query template indicating one or more example integration flows and comprising a request to generate a natural language description of the integration flow, the query template selected from a plurality of query templates selected based at least in part on the request;
transmitting the query to the LLM;
receiving, from the LLM, a response comprising the integration flow and the natural language description;
extracting the integration flow and the natural language description from the response; and
performing a validation process on the integration flow based at least in part on one or more integration flow validation rules.