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.
Reduces latency by calling data stores directly
upon receiving a user utterance at each turn,
bypassing metadata personalization and data store filters.
Once enabled,
choose options to decide if you want the playbook to wait
for the next user utterance after receiving data store responses.
[[["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 2025-04-17 UTC."],[[["This product or feature is subject to the \"Pre-GA Offerings Terms\" and is available \"as is\" with potentially limited support, as detailed in the Service Specific Terms."],["Playbook-specific settings are available in addition to agent-level settings, allowing for greater customization."],["Data store RAG acceleration can be enabled to reduce latency by directly calling data stores and bypassing metadata personalization and filters."],["Advanced speech settings, manual speech adaptation, and DTMF settings can be configured, with detailed guides available for each."]]],[]]
