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.
Stay organized with collections
Save and categorize content based on your preferences.
If you have an existing Conversational Agents (Dialogflow CX) agent,
you can upgrade this agent to a hybrid agent,
which combines the power of precise conversation controls
(flows, parameters, intents, conditions, transitions, and so on)
with data store handler generative features.
As part of this upgrade,
you may wish to delete or temporarily disable intent routes
(while testing data store handlers)
for certain conversation scenarios from your agent,
because the data store handlers can handle those scenarios more simply.
Recommended scenarios
The following scenarios are recommended for data store handlers:
Questions that can be answered by your organization's documents or website.
FAQs that do not require database lookups.
The following scenarios are not recommended for data store handlers:
Content that does not have answers to desired questions.
Questions that require database lookups or server requests.
Scenarios that require data redaction.
Scenarios that require deterministic agent responses.
Input evaluation order
Conversational Agents (Dialogflow CX) evaluates end-user input in the following order
for hybrid agents:
[[["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 2025-08-28 UTC."],[[["\u003cp\u003eHybrid agents combine precise conversation controls with data store handler generative features.\u003c/p\u003e\n"],["\u003cp\u003eData store handlers are recommended for questions answerable by documents/websites or FAQs not needing database lookups.\u003c/p\u003e\n"],["\u003cp\u003eData store handlers are not ideal for content lacking answers, questions needing database lookups, data redaction, or deterministic responses.\u003c/p\u003e\n"],["\u003cp\u003eIn hybrid agents, input is evaluated first through parameter input, then intent matches, and finally, data store handlers with FAQ or unstructured data content.\u003c/p\u003e\n"]]],[],null,["# Data store hybrid agents\n\nIf you have an existing Conversational Agents (Dialogflow CX) agent,\nyou can upgrade this agent to a *hybrid agent*,\nwhich combines the power of precise conversation controls\n(flows, parameters, intents, conditions, transitions, and so on)\nwith data store handler generative features.\n\nAs part of this upgrade,\nyou may wish to delete or temporarily disable intent routes\n(while testing data store handlers)\nfor certain conversation scenarios from your agent,\nbecause the data store handlers can handle those scenarios more simply.\n\nRecommended scenarios\n---------------------\n\nThe following scenarios are recommended for data store handlers:\n\n- Questions that can be answered by your organization's documents or website.\n- FAQs that do not require database lookups.\n\nThe following scenarios are not recommended for data store handlers:\n\n- Content that does not have answers to desired questions.\n- Questions that require database lookups or server requests.\n- Scenarios that require data redaction.\n- Scenarios that require deterministic agent responses.\n\nInput evaluation order\n----------------------\n\nConversational Agents (Dialogflow CX) evaluates end-user input in the following order\nfor hybrid agents:\n\n1. Parameter input while form filling.\n2. Intent matches for [routes in scope](/dialogflow/cx/docs/concept/handler#route).\n3. Data store handler with FAQ data store content.\n4. Data store handler with unstructured data store content."]]
