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.

Data store performance improvements

This guide provides recommendations for monitoring and improving the performance of data store handlers.

Track your agent's performance

You can monitor your agents conversation history and you can use the analytics tool for agent statistics.

Run self-service evaluation

You can run self-service evaluation which will assess the quality of your data store agent and recommend changes.

Improve agent responses

If you find some responses during testing that don't meet your expectations, try the following.

You can overwrite an answer by adding an FAQ entry for a specific question.
If you are experiencing low quality answers with a structured FAQ, try using unstructured FAQ.
Using search configurations helps to ensure that the correct answers are provided.
Use the parse and chunk configurations to optimize responses.
To ban certain phrases, see agent settings: banned phrases.
To customize Responsible AI (RAI) content filtering, see agent settings: safety filters.

Optimization of data store tools used by Playbooks

This setting accelerates a data store's RAG response and improves latency by not rewriting the user query nor dynamically populating tool parameters. This means that the user query is passed to the data store as-is and no filters or user metadata-related parameters are populated.

You can enable this feature in the Dialogflow CX console by selecting the playbook, then clicking the Settings tab. You have the option of configuring the Playbook to continue processing any follow-up actions immediately or waiting for the next end-user input.

If enabled, the following Playbook instructions are still honored:

When to answer the user query using the data store(s).
When not to answer user query using the data store(s) and instead provide an alternate response.
Any instructions that are defensive such as, for example, "don't answer questions about competitors".

If enabled, the following Playbook instructions are ignored. Don't activate this setting if you have any of the following query requirements:

Specific data store filters to be populated using the instructions.
Instructions to apply any user personalization metadata passed by filters.
Any other instructions to rewrite the user query before querying the data store.

Handle conversation digressions

An end-user may ask clarifying questions during a conversation. For example, during credit card information collection, they may want to clarify what a CVV is. In this case, your agent should answer the question and return to collecting the necessary credit card information. To accomplish this, you can create a data store handler with data stores that answer the question, apply that handler to the flow start page of the flow that handles credit card information collection, and set a transition target for this handler to return to the "current page".

Handle undesired intent matches

If your agent is matching intents when it should be using a data store handler, you can try the following to correct this:

Delete or modify training phrases that are vague, so that all of your training phrases precisely handle the desired intention and do not conflict with your data store content.
Use negative examples to avoid intent matching.

Data store filtering

In some cases, you may only want certain data stores available for queries, depending on session parameter values. For example, you may have unique data stores for product categories. To accomplish data store filtering for product categories:

Set session parameters to product categories.
Create condition routes that check the values of the session parameters and transition to a specific page that has the desired data store handler.
The data store handler should transition back to the calling page, so that the conversation can continue.

Personalization

To make generative answers more relevant to end-users, you can provide Conversational Agents (Dialogflow CX) with information about users.

This information is provided as JSON. There is no expected schema, so you are free to define the object properties. This JSON is sent to the large language model as-is, so descriptive property names and values lead to the best results.

For example:

{
  "subscription plan": "Business Premium Plus",
  "devices owned": [
    {"model": "Google Pixel 7"},
    {"model": "Google Pixel Tablet"}
  ]
}

Personalizing with the API

You can provide this data to Conversational Agents (Dialogflow CX) when sending detect intent requests. This information must be provided in every detect intent request, because it is not persisted in the session.

Provide this information in the queryParams.endUserMetadata field in the Sessions.detectIntent method.

Select a protocol and version for the Session reference:

Protocol	V3	V3beta1
REST	Session resource	Session resource
RPC	Session interface	Session interface
C++	SessionsClient	Not available
C#	SessionsClient	Not available
Go	SessionsClient	Not available
Java	SessionsClient	SessionsClient
Node.js	SessionsClient	SessionsClient
PHP	Not available	Not available
Python	SessionsClient	SessionsClient
Ruby	Not available	Not available

Personalizing with Dialogflow CX Messenger

You can provide this data to the Dialogflow CX Messenger integration. See the setContext method.

Search configuration

To have better control over the agent behavior and improve the quality of the answers, boost and filter search configurations are exposed to let you boost, bury and filter documents.

Boost controls enable you to change search result ranking by applying a boost value (greater than zero for higher ranking, less than zero for lower ranking) to specific documents.

Filter controls let you to either keep or remove search results based on the specified filter criteria.

This information is provided as JSON to Conversational Agents (Dialogflow CX) requests. The format of the JSON depends on the search control type.

Boost control

The following search configuration describes a boost control:

"searchConfig": {
  "boostSpecs": [
    {
      "dataStores": [ "DATASTORE_ID" ],
      "spec": [
        {
          "conditionBoostSpecs": {
            "condition": "CONDITION",
            "boost": "1.0"
          }
        }
      ]
    }
  ]
}

Filter control

The following search configuration describes a filter control:

"searchConfig": {
  "filterSpecs": [
    {
      "dataStores": [ "DATASTORE_ID" ],
      "filter": "CONDITION"
    }
  ]
}

Setup search configuration with the API

Provide this information in the queryParams.searchConfig field in the Sessions.detectIntent method.

Select a protocol and version for the Session reference:

Protocol	V3	V3beta1
REST	Session resource	Session resource
RPC	Session interface	Session interface
C++	SessionsClient	Not available
C#	SessionsClient	Not available
Go	SessionsClient	Not available
Java	SessionsClient	SessionsClient
Node.js	SessionsClient	SessionsClient
PHP	Not available	Not available
Python	SessionsClient	SessionsClient
Ruby	Not available	Not available

Setup search configuration with Dialogflow CX Messenger

You can provide this data to the Dialogflow CX Messenger integration.

To apply a search control, the following snippet needs to be added to the messenger code when embedding it into a website:

<script>
  document.addEventListener('df-messenger-loaded', () => {
    const dfMessenger = document.querySelector('df-messenger');
    const searchConfig = { ... }
    dfMessenger.setQueryParameters(searchConfig);
  });
</script>

See the setQueryParameters method.

Data store settings

Data store hybrid agents