As organizations scale coding agents like Codex across engineering teams, they need visibility into adoption, consumption, reliability, and access. Codex can emit OpenTelemetry (OTel) metrics; when local Codex clients use OpenAI models through Amazon Bedrock and authenticate with AWS IAM Identity Center, these metrics route through a local OTel collector to Amazon CloudWatch. This provides an AWS native view of Codex usage organized by user, team, department, organization, or cost center, without adding a centralized proxy. A collector on each developer workstation enriches metrics with organizational context and sends them to the regional CloudWatch OpenTelemetry Protocol (OTLP) endpoint using AWS Signature Version 4 (SigV4). The reference deployment creates a CloudWatch dashboard. The bundled CodexOnBedrock dashboard includes rolling 24-hour totals for active users, conversation turns, API requests, and token usage, plus views by model, token type, user, department, team, cost center, organization, and session source. These signals help leaders distinguish broad adoption from isolated experimentation. Tool-call activity shows where agentic workflows are taking hold, while request and duration metrics support investigation of degraded experiences. Executive questions addressed include whether adoption is expanding, where consumption is concentrated, whether teams use agentic capabilities, and whether the developer experience is reliable. AWS Cost and Usage Reports (CUR) 2.0 with IAM principal data supports billing-grade financial reporting and allocation.