Amazon Web Services launched CloudWatch Coding Agent Insights on July 20, giving engineering teams ready-made dashboards for OpenTelemetry metrics from Claude Code, OpenAI Codex and GitHub Copilot. The dashboards track usage, cost, latency, tool calls and approvals, but AWS says identity and organizational fields must be emitted as OpenTelemetry resource attributes for the views to populate correctly.
Amazon Web Services launched CloudWatch Coding Agent Insights on July 20, adding ready-made dashboards for OpenTelemetry metrics emitted by Claude Code, OpenAI Codex and GitHub Copilot. AWS says the feature is intended to help engineering leaders examine agent adoption, spending, delivery activity and model cost alongside existing CloudWatch operational data.
The feature is available in AWS commercial regions except Middle East (UAE), Middle East (Bahrain) and Israel (Tel Aviv). Standard CloudWatch OpenTelemetry metric-ingestion pricing applies.
What the dashboards require
AWS documentation says the dashboards appear automatically under GenAI Observability after an agent begins sending metrics in the expected shape. The supported telemetry includes token consumption, per-turn latency, tool calls, API requests and approvals. Teams can segment the data by organization, department, team, cost center and user, export it as CSV, or query the metrics with PromQL.
The schema requirement is central to the release. Native agent metrics provide dimensions such as model and token_type, while fields including user.email, team.id, department, cost_center and organization must be sent as OpenTelemetry resource attributes. AWS warns that changing metric names or moving identity fields off the resource can prevent the dashboards from populating.
Enterprise setup and interpretation
AWS documents a self-hosted Claude apps gateway for enterprise Claude Code deployments. The gateway can authenticate developers through a corporate identity provider, hold upstream credentials, enforce group-based model access and managed settings, and route identity-stamped telemetry to CloudWatch or other collectors. AWS lists Claude Code 2.1.195 or later, an OpenID Connect provider, PostgreSQL 14 or later, TLS and a private-network address among the prerequisites.
For data and platform teams, the practical work extends beyond enabling a dashboard. User identities, team labels and cost-center fields need consistent definitions, controlled access and appropriate retention. Measures such as token volume, commits or pull requests can describe activity and cost, but they do not by themselves establish productivity or business value. That distinction is LDS interpretation; AWS documents the available metrics and proposed analyses, not a universal productivity methodology.
Key Points #
- 1CloudWatch Coding Agent Insights provides ready-made dashboards for OpenTelemetry metrics from Claude Code, OpenAI Codex and GitHub Copilot.
- 2AWS requires organizational and identity fields to be emitted as OpenTelemetry resource attributes for reliable dashboard population and attribution.
- 3The dashboards expose activity and cost signals, but teams still need governance and a separate method for evaluating engineering value.
Scoring Rationale #
The release adds a practical observability workflow for organizations deploying multiple AI coding agents, with direct relevance to platform engineering and FinOps. Its impact is constrained by its CloudWatch-specific implementation and by the schema and governance work required before the dashboards are reliable.
Sources #
Primary source and supporting public references used for this report.
Practice with real Retail & eCommerce data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Retail & eCommerce problems