Grok Build Observability & Monitoring with OpenTelemetry

XAI's terminal coding agent Grok Build now supports full observability via OpenTelemetry, emitting metrics and structured events that can be monitored in SigNoz. The integration requires setting the GROK_EXTERNAL_OTEL master switch and an exporter, with metrics covering token usage, turns, tool calls, errors, and startup timings. SigNoz provides a Metrics Explorer and Logs Explorer to visualize these signals, enabling teams to track token spend, model usage, tool adoption, and failure reasons.

What is Grok Build Observability? Grok Build https://github.com/xai-org/grok-build is xAI's terminal coding agent. It ships its own OpenTelemetry exporter, so instrumenting it is a matter of configuration: there is no library to install and no collector to run. Once enabled, it emits metrics covering token usage, turns, tool calls, errors, and startup timings, plus a stream of structured events for each session. With full Grok Build observability in SigNoz, you can see how much your team is spending in tokens and on which models, which tools the agent actually reaches for, how often turns fail and why, and where startup time is going. Prerequisites - SigNoz setup choose one : SigNoz Cloud account https://signoz.io/teams/ with an active ingestion key- Self-hosted SigNoz instance - Grok Build installed. See the xAI installation guide https://docs.x.ai/build/overview - A SuperGrok subscription or an XAI API KEY Monitor Grok Build with OpenTelemetry Grok Build's telemetry is a double opt-in. The GROK EXTERNAL OTEL master switch and at least one exporter must both be set, since either alone emits nothing. Step 1: Launch Grok Build with telemetry enabled export GROK EXTERNAL OTEL=1 export OTEL METRICS EXPORTER=otlp export OTEL LOGS EXPORTER=otlp export OTEL EXPORTER OTLP PROTOCOL=http/protobuf export OTEL EXPORTER OTLP ENDPOINT="https://ingest.<region .signoz.cloud:443" export OTEL EXPORTER OTLP HEADERS="signoz-ingestion-key=<your-ingestion-key " export OTEL METRIC EXPORT INTERVAL=10000 grok Verify these values: <region : Your SigNoz Cloud region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint . <your-ingestion-key : Your SigNoz ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ . Step 2: Generate some telemetry Run a few prompts that make the agent read files or run commands, so tool and token metrics have something to report. grok -p "List the files in this directory and summarise what this project does." The default metric export interval is 60 seconds, which is why the snippet above lowers it to 10 seconds while you verify the pipeline. Events are exported every 5 seconds by default. View Grok Build Metrics in SigNoz Metrics are Grok Build's primary signal. Open the Metrics Explorer https://signoz.io/docs/metrics-management/metrics-explorer/ , search for grok code.token.usage , and run the query to confirm data is arriving. Every metric lives under the ai.xai.grok code meter scope. All the counters are monotonic delta sums, so aggregate them with increase to get totals rather than rate . | Metric | Unit | Key attributes | |---|---|---| grok code.session.count | {session} | base attributes only | grok code.turn.count | {turn} | outcome completed , cancelled , error , model | grok code.token.usage | {token} | type input , output , reasoning , cache read , model | grok code.tool.usage | {call} | tool name , outcome | grok code.tool.decision | {decision} | tool name , decision , access kind , permission mode | grok code.error.count | {error} | error category , model | grok code.startup.total | ms | outcome , auth mode | grok code.startup.phase duration | ms | phase , outcome , auth mode | View Grok Build Logs in SigNoz Open the Logs Explorer https://signoz.io/docs/userguide/logs query builder/ and filter with service.name = 'grok-cli' to see the event stream. Each event carries its detail in attributes rather than in the log body, so open a record to inspect it. Useful attributes include model , input tokens , output tokens , cache read tokens , reasoning tokens , tool name , outcome , and duration ms . Every event also carries session.id and prompt.id , so you can group everything produced while handling a single prompt. Grok Build Observability Dashboard The Grok Build dashboard https://signoz.io/docs/dashboards/dashboard-templates/grok-build-dashboard/ gives you token usage by type and model, tool activity, error categories, and startup latency out of the box. Troubleshooting Grok Build Observability No data in SigNoz Check that both GROK EXTERNAL OTEL=1 and at least one exporter are set. Either on its own emits nothing. Then run grok --debug and search the log under ~/.grok/debug/ for external otel: lines, which report whether the stream resolved its configuration and whether exports are succeeding. Metrics are missing but events arrive The two signals have different export intervals. Metrics default to 60 seconds while events default to 5, so metrics can look absent for a full minute after startup. Set OTEL METRIC EXPORT INTERVAL=10000 while you verify. Nothing arrives for the first few seconds Grok Build holds telemetry closed at startup until it has fetched fleet policy from xAI, since that policy can disable the stream. The wait is bounded and emission begins within 30 seconds regardless. Export errors mentioning gRPC Set OTEL EXPORTER OTLP PROTOCOL=http/protobuf . gRPC is documented as supported but does not work in version 1.0.3. Related integrations Instrument the other AI coding agents you run, using the same OpenTelemetry pipeline: Monitor OpenAI Codex with OpenTelemetry https://signoz.io/docs/codex-monitoring/ - track Codex CLI sessions, token spend, and command-level traces Claude Code monitoring with OpenTelemetry https://signoz.io/docs/claude-code-monitoring/ - track token usage, costs, and tool decisions OpenCode observability with OpenTelemetry https://signoz.io/docs/opencode-observability/ - trace OpenCode sessions, tool calls, and per-message cost Browse all LLM observability integrations https://signoz.io/docs/llm-observability/ to instrument the rest of your stack. Additional resources: