# Datadog AI integration on Definable

> Datadog offers monitoring, observability, and security for cloud-scale applications, unifying metrics, logs, and traces to help teams detect issues and optimize performance

## What this connects

Datadog offers monitoring, observability, and security for cloud-scale applications, unifying metrics, logs, and traces to help teams detect issues and optimize performance

Vendor: https://www.datadoghq.com

## Tools available

**43** tools available. First 12:

- `DATADOG_CREATE_DASHBOARD` — Create Dashboard — Create a dashboard in Datadog. Dashboards provide customizable visualizations for monitoring your infrastructure, applications, and business metrics in a unified view.
- `DATADOG_CREATE_DOWNTIME` — Create downtime — Creates a new downtime in Datadog to suppress alerts during maintenance windows or planned outages. Useful for preventing false alarms during deployments or maintenance.
- `DATADOG_CREATE_EVENT` — Create event — Creates a new event in Datadog. Events are useful for tracking deployments, outages, configuration changes, and other important occurrences.
- `DATADOG_CREATE_MONITOR` — Create monitor — Creates a new Datadog monitor to track metrics, logs, or other data sources with configurable alerting thresholds and notifications.
- `DATADOG_CREATE_SLO` — Create SLO — Create a Service Level Objective (SLO) in Datadog. SLOs help you define and track reliability targets for your services, enabling data-driven decisions about service quality and reliability investments.
- `DATADOG_CREATE_SYNTHETIC_API_TEST` — Create Synthetic API Test — Create a synthetic API test in Datadog. Creates a new synthetic API test that continuously monitors API endpoints from multiple locations worldwide. Useful for proactive monitoring of API uptime, performance, and functionality.
- `DATADOG_CREATE_WEBHOOK` — Create Webhook — Create a webhook in Datadog. Registers a named destination endpoint; each monitor must explicitly reference the webhook by name in its message or notification settings for alerts to be delivered.
- `DATADOG_DELETE_DASHBOARD` — Delete Dashboard — Delete a dashboard in Datadog. Permanently removes a dashboard from your organization. This action cannot be undone. Use with caution.
- `DATADOG_DELETE_MONITOR` — Delete monitor — Deletes a Datadog monitor permanently. Use with caution as this action cannot be undone.
- `DATADOG_GET_DASHBOARD` — Get Dashboard — Get a specific dashboard from Datadog. Retrieves detailed information about a dashboard including its widgets, layout, template variables, and metadata.
- `DATADOG_GET_MONITOR` — Get monitor — Retrieves detailed information about a specific Datadog monitor, including its current state, configuration, and any active downtimes.
- `DATADOG_GET_SERVICE_DEPENDENCIES` — Get Service Dependencies — Get service dependency mapping from Datadog APM. This action retrieves the dependency graph for a specific service, showing both upstream services (that call this service) and downstream services (that this service calls). It's essential for: - Understanding the blast radius of service failures - Identifying critical dependencies during incidents - Analyzing service communication patterns - Planning architectural changes - Monitoring service health in context The dependency information includes call rates, error rates, and latency metrics to help assess the health of service relationships. Requires APM instrumentation on the target service; uninstrumented services return empty or incomplete dependency data.

## Auth

Auth schemes: `OAUTH2`, `API_KEY`.

## How agents use Datadog

Inside a Definable workflow, Datadog is one of the tools the **Distributor specialist** can call. Example coordination patterns:

- **Researcher → Datadog** — the Researcher (GPT-5.5) pulls context from Datadog (records, threads, documents), synthesises findings, and briefs the rest of the team.
- **Writer → Distributor → Datadog** — the Writer (Claude Opus 4.7) drafts copy in brand voice, the Verifier passes it, then the Distributor writes the result into Datadog (create record, post message, draft email).
- **Designer / Engineer → Distributor → Datadog** — the Designer ships an asset or the Engineer ships a code change, the Distributor delivers it via Datadog (attach file, open PR comment, post status).

The Verifier checks every Datadog call. On rate limit, schema drift, or auth refresh it self-heals and retries — the workflow completes without manual intervention.

## Categories

- server monitoring — https://definable.ai/apps/category/server-monitoring/
- developer tools — https://definable.ai/apps/category/developer-tools/

## Related

- HTML page: https://definable.ai/apps/datadog/
- Same category (server monitoring): https://definable.ai/apps/category/server-monitoring/
- All integrations: https://definable.ai/apps/
- Workflow (multi-agent loop): https://definable.ai/workflow/
- Apps llms.txt index: https://definable.ai/llms-apps.txt