---
title: OCI Generative AI Agents
description: >-
  Monitor invocations, latency, and errors for OCI Generative AI Agents
  endpoints.
breadcrumbs: Docs > Integrations > OCI Generative AI Agents
---

> For the complete documentation index, see [llms.txt](https://docs.datadoghq.com/llms.txt).

# OCI Generative AI Agents
Integration version1.0.0
{% callout %}
# Important note for users on the following Datadog sites: us2.ddog-gov.com

{% alert level="info" %}
To find out if this integration is available in your organization, see your [Datadog Integrations](https://app.datadoghq.com/integrations) page or ask your organization administrator.

To initiate an exception request to enable this integration for your organization, email [support@ddog-gov.com](mailto:support@ddog-gov.com).
{% /alert %}

{% /callout %}

## Overview{% #overview %}

Oracle Cloud Infrastructure (OCI) Generative AI Agents is a fully managed service that combines large language models with retrieval and tools to build AI agents hosted on endpoints.

This integration helps you monitor invocations, latency, character usage, and errors for your OCI Generative AI Agents endpoints by collecting metrics and tags from the [`oci_generativeaiagent`](https://docs.oracle.com/en-us/iaas/Content/generative-ai-agents/metrics.htm) namespace.

## Setup{% #setup %}

### Installation{% #installation %}

After you set up the [Oracle Cloud Infrastructure](https://docs.datadoghq.com/integrations/oracle_cloud_infrastructure.md) integration, verify the `oci_generativeaiagent` namespace is included in your [Connector Hub](https://cloud.oracle.com/connector-hub/service-connectors).

## Data Collected{% #data-collected %}

### Metrics{% #metrics %}

|  |
|  |
| **oci.generativeaiagent.client_error_count**(count)      | The number of calls that failed with a client-side error.*Shown as error*                |
| **oci.generativeaiagent.error_trace_count**(count)       | The number of traces with an error. Applies only if tracing is enabled for the endpoint. |
| **oci.generativeaiagent.input_characters_count**(count)  | The number of input characters processed by the agent hosted on the endpoint.            |
| **oci.generativeaiagent.invocation_latency**(gauge)       | The total processing time for a call to finish.*Shown as millisecond*                    |
| **oci.generativeaiagent.output_characters_count**(count) | The number of output characters processed by the agent hosted on the endpoint.           |
| **oci.generativeaiagent.server_error_count**(count)      | The number of calls that failed with a service-side error.*Shown as error*               |
| **oci.generativeaiagent.total_invocation_count**(count)  | The number of calls processed by the agent hosted on the endpoint.*Shown as invocation*  |

### Events{% #events %}

The OCI Generative AI Agents integration does not include any events.

### Service Checks{% #service-checks %}

The OCI Generative AI Agents integration does not include any service checks.

## Troubleshooting{% #troubleshooting %}

Need help? Contact [Datadog support](https://docs.datadoghq.com/help/).
