Datadog Agent Observability

Datadog

Formerly Datadog LLM Observability

Vendor

Datadog module for end-to-end tracing of LLM and agent apps, with cost/latency dashboards, quality clustering and sensitive-data redaction.

Curated by Tiberiu ArvaVerified 2026-09-30

Proprietary

Docs Website

Strengths

Correlates LLM spans with existing APM data
Built-in sensitive-data scanning and redaction
SDKs for Python, Node.js and Java

Practitioner note

Best fit for organisations already standardised on Datadog that want LLM traces next to infrastructure and APM data under existing audit and compliance controls. Span-based billing grows with agent step count, so model cost before instrumenting chatty multi-step agents.

Warning

Datadog Agent Observability: Datadog's docs now title the product "Agent Observability" and still use "LLM Observability" interchangeably. Not available on the US1-FED/US2-FED government sites (checked 2026-09-30).

Governance posture

Reviewed 2026-09-30

YesData residency

The customer picks a Datadog site: US1/US3/US5, EU1 (Germany), AP1 (Japan), AP2 (Australia) or UK1. The product is not supported on FED sites.

Source

YesDeployment model

Datadog-hosted SaaS only. (saas)

Source

YesAudit logging

Datadog Audit Trail records user activity, API requests and resource changes across the organisation.

Source

YesSOC 2

Datadog lists SOC 2 Type 2 on its Trust Center (company-wide; product-level scope not separately stated).

Source

YesISO 27001

Datadog lists ISO/IEC 27001 (plus 27017, 27018 and 27701) on its Trust Center.

Source

YesISO 42001

Datadog lists ISO/IEC 42001:2023 on its Trust Center (company-wide; module scope not separately stated).

Source

N/AEU AI Act

Monitoring tooling, not an AI system placed on the market. Obligations rest with the deployer of the monitored system. (role: not-applicable)

YesLicense risk

Proprietary SaaS tied to the Datadog platform, with span-based metered billing. (medium)

Source

EU AI Act obligations

Risk tier: Not applicable · as of 2026-08-23

Source-backed information mapped from Datadog Agent Observability's tracked risk tier — not legal advice. Obligations depend on how your organisation deploys the system; see the full obligation reference and timeline.

This record's EU AI Act risk tier is marked not applicable, so no tier-specific obligations attach. Deployers embedding it in an AI system in scope of the Act should assess that system's own tier.

Explore the category

Compare this tool against the rest of its category and the cloud platform foundation layer.

AI Observability & Evaluation

Return to the category grid to compare governance posture across every tracked tool.

Platforms

Review Microsoft Foundry, Amazon Bedrock, and Gemini Enterprise Agent Platform as the foundation layer.

Weekly updates

Track releases, deprecations, license changes, and other market movements.