Some products and features are in the process of being renamed. Generative playbook and flow features are also being migrated to a single consolidated console. See the details.
To filter out false positive results and still get variety in matched natural language inputs for your agent, you can tune the machine learning classification threshold. If the returned score value is less than the threshold value, then a no-match event will be triggered. The score values range from 0.0 (completely uncertain) to 1.0 (completely certain). If set to 0.0, the default of 0.3 is used. You can set a separate classification threshold for the flow in each language enabled for the agent.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-03-05 UTC."],[[["This document outlines settings related to Natural Language Understanding (NLU) within a system, detailing the available configurations for model behavior."],["The `modelType` setting specifies the type of NLU model, allowing for choices between `MODEL_TYPE_STANDARD` and `MODEL_TYPE_ADVANCED`, with `MODEL_TYPE_UNSPECIFIED` defaulting to standard."],["The `classificationThreshold` setting controls the sensitivity of the system, allowing the configuration of the minimum score to avoid false positives, with a range from 0.0 to 1.0, defaulting to 0.3 when set to 0.0."],["The `modelTrainingMode` setting dictates how the NLU model is trained, either `MODEL_TRAINING_MODE_AUTOMATIC`, which triggers training upon flow modification, or `MODEL_TRAINING_MODE_MANUAL`, requiring manual initiation, with the former being used by default when `MODEL_TRAINING_MODE_UNSPECIFIED` is used."]]],[]]