> ## Documentation Index
> Fetch the complete documentation index at: https://dialnexa.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Google BigQuery Voice AI Integration Guide

> Plan a Google BigQuery integration with DialNexa voice AI. Choose a connection method, map call data, test updates, and handle failures safely.

The **Google BigQuery voice AI integration** is useful when a DialNexa call needs information from Google BigQuery or when a verified call outcome should update Google BigQuery. This page helps you choose a connection method, map the required data, and test the workflow safely.

<Warning>
  A catalog page describes a possible workflow. It does not confirm that a native Google BigQuery connector is enabled in your workspace. Check **Integrations** in the DialNexa dashboard first. If Google BigQuery is not listed, use a custom function, agent webhook, or external automation service.
</Warning>

## When to use the Google BigQuery voice AI integration

Use Google BigQuery when:

* Your team already relies on Google BigQuery as a source of customer or operational data.
* The agent needs current Google BigQuery information to answer or route a caller correctly.
* A call outcome should create, update, or notify something in Google BigQuery.
* The receiving team will act on the record after the call.

Do not add the integration only because it appears in the catalog. Start with one action that removes a real manual handoff.

## Before you begin

Prepare the following:

* A published DialNexa agent that has already passed a basic test call.
* Access to the DialNexa workspace **Integrations** page.
* A Google BigQuery account with permission to read or update the required records.
* One test record that does not affect a live customer.
* A list of actions that can run automatically and actions that require human review.

## Choose how to connect Google BigQuery

| Connection method                                   | Use it when                                                       | Important limit                                                             |
| --------------------------------------------------- | ----------------------------------------------------------------- | --------------------------------------------------------------------------- |
| Workspace connector                                 | Google BigQuery appears in your DialNexa **Integrations** page    | Available actions and authentication depend on your workspace               |
| [Custom function](/docs/agent-settings/custom-functions) | The agent needs Google BigQuery data during the live conversation | Keep the request fast and return only the fields the agent needs            |
| [Agent webhook](/docs/api-access/agent-webhooks)         | Google BigQuery should receive a result after the call            | Your endpoint must authenticate, retry safely, and prevent duplicate writes |
| External automation                                 | The workflow spans Google BigQuery and several other systems      | Monitor the external workflow separately from the DialNexa call             |

## Build the Google BigQuery voice AI workflow

1. Define the exact event that starts the action, such as a confirmed booking, qualified lead, support escalation, or completed call.
2. Choose the connection method from the table above.
3. Map caller identity, the DialNexa call ID, the verified outcome, and the destination record ID.
4. Add a condition so uncertain, sensitive, destructive, or high-value changes go to a human-owned queue.
5. Store the destination record URL or ID with the call result so your team can trace the handoff.
6. Test success, no-match, duplicate, permission-error, and timeout cases before using live traffic.

## Data to map between DialNexa and Google BigQuery

* DialNexa call ID, call direction, status, and final outcome
* Caller name, phone number, email, and matched customer or account ID
* Structured fields collected during the call, including consent where required
* Short operational summary, requested next step, owner, and due date
* Transcript or recording link only when your privacy policy allows it
* Google BigQuery record ID, record URL, update timestamp, and integration result

## Google BigQuery actions to evaluate

The following examples come from the catalog metadata or common workflow patterns. Confirm the current action name, required fields, permissions, and limits in your Google BigQuery account before implementation.

* Search all bigquery reservation assignments
* Create bigquery connection

Start with one low-risk read or write. Add more actions only after the first handoff is reliable.

## Verify the Google BigQuery integration

Run a test call and confirm that:

1. The workflow finds the intended Google BigQuery record instead of creating a duplicate.
2. Only the approved fields change.
3. The DialNexa call ID is stored for traceability and retry protection.
4. A failed request creates a visible error or human-owned task.
5. The receiving owner can open the Google BigQuery record and understand the next step without reading the full transcript.

## Troubleshoot Google BigQuery integration issues

| Problem                                       | What to check                                                                                                                                     |
| --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------- |
| Google BigQuery is not shown in the dashboard | Use a custom function, webhook, or external automation service, or [request the integration](/docs/dashboard-integrations/requesting-new-integrations) |
| Authentication fails                          | Reconnect the account and verify scopes, workspace ownership, and token expiry                                                                    |
| No matching record is found                   | Normalize phone numbers and email addresses, then define a clear create-versus-review rule                                                        |
| Duplicate updates appear                      | Use the DialNexa call ID as an idempotency key and make retries safe                                                                              |
| The live call becomes slow                    | Move nonessential writes to a post-call webhook and keep live lookups small                                                                       |

## Related pages

* [DialNexa integrations overview](/docs/integrations/overview)
* [Connect dashboard integrations](/docs/dashboard-integrations/connecting-integrations)
* [Use integrations in agents](/docs/dashboard-integrations/using-integrations-in-agents)
* [Use integrations in workflows](/docs/dashboard-integrations/using-integrations-in-workflows)
* [Integration workflow tutorials](/docs/tutorials/integration-workflows)