You need to monitor a new microservice you just deployed, but building a dashboard from scratch means clicking through metrics, logs, and traces and configuring visualization panels.
You open your AI assistant, connected to SigNoz via the MCP server, and ask it to build the dashboard for you.
Prerequisites
- Connect your AI assistant to SigNoz using the MCP Server guide.
Step 1: Create the Dashboard from a Natural Language Prompt
Confirm the recommendation service is sending data. Then search for its relevant data and create a dashboard with three panels: p99 latency, error rate, and request throughput.
Your assistant will first verify the service exists and is actively sending telemetry data, then build the dashboard:
ā Service confirmation: The recommendation service is actively sending data
- 3,342 calls over the last 24 hours
- Primary operation: oteldemo.RecommendationService/ListRecommendations
- Current error rate: ~4.28%
ā Dashboard created: "Recommendation Service Overview"
- Dashboard ID: 019dad7d-a6b2-7269-b5a0-65e0ebd42924
Three panels configured (all scoped to service.name = 'recommendation' over last 24h):
1. P99 Latency (top-left)
- Metric: p99(durationNano) on traces
- Visualization: Time series
2. Error Rate (%) (top-right)
- Formula: (error spans / total spans) Ć 100
- Visualization: Time series
3. Request Throughput (req/s) (full-width, bottom)
- Metric: rate() on traces
- Visualization: Time series
You can open it in SigNoz under Dashboards ā "Recommendation Service Overview"
The dashboard is now live with all three panels displaying real-time metrics for the recommendation service.
Final Summary
You now have a fully functional dashboard created from just using a simple prompt.
Under the Hood
During this workflow, the MCP server called these tools:
| Step | MCP Tool | What It Did |
|---|---|---|
| 1 | signoz_list_services | Verified the recommendation service exists and is actively sending telemetry data |
| 1 | signoz_aggregate_traces | Retrieved p99 latency, error rate, and request throughput metrics over the last 24 hours |
| 1 | signoz_create_dashboard | Created the dashboard with three panels configured for the recommendation service |
Related Use Cases
- Incident Specific Dashboard Spin-Up - Instantly generate focused dashboards for active incidents with relevant metrics and traces.
- Alert Correlation Analysis - When multiple services alert simultaneously, identify whether it's a cascade from one failure or separate incidents.
- Post Deployment Monitoring - Compare key metrics before and after a deployment to detect performance regressions or unexpected changes.
If you need help with the steps in this topic, please reach out to us on SigNoz Community Slack.
If you are a SigNoz Cloud user, please use in product chat support located at the bottom right corner of your SigNoz instance or contact us at cloud-support@signoz.io.
