Salesforce Introduces Koa Decisions Model for Fast Agent Choices
Salesforce has introduced Koa Decisions, a new decision model that reads a request and a list of categories and returns one choice, a yes-or-no answer, or a score in a single step. It is the next version of Salesforce’s HyperClassifier and was built by applying new training techniques to Google’s Gemma, adding support for images and audio. Salesforce says the model is aimed at routing and other quick choices inside agent workflows, while leaving larger language models for writing and reasoning. People can try a demo through a free Trailhead account. Salesforce plans to extend Koa Decisions to flows, Apex, prompt templates and a developer API.
Why it matters
Decision models can handle routine choices such as routing a support request much faster than a general-purpose LLM, which Salesforce says can reserve the larger model for writing and reasoning. That can make agent workflows more responsive and use less computing for simple decisions.
Sources
- PrimarySalesforce
Written by AIToolMaps from the source above and checked against it sentence by sentence.