Grafana Tempo with NeuBird, the AI SRE: from slow span to root cause
NeuBird queries your Grafana Tempo traces at investigation time, then correlates the slow and failing spans with the rest of your stack to find the cause.
< 5 min
Root cause, at 94% accuracy
15+
Sources queried in parallel per investigation
In place
No bulk telemetry stored
< 1 hour
To deploy on the stack you already run
Core Capabilities
From signals to solutions
Resolve
Follow the request to the failing hop
When latency or errors spike, NeuBird searches Tempo with TraceQL for the slow and failing traces in the incident window, finds the span where the time or the error starts, and checks that service against your metrics, logs, Kubernetes state and deploy history in parallel. It returns the causal chain with the trace IDs attached.
- Pinpoints the downstream span behind an upstream timeout
- Ties error spans to the deploy or config change that preceded them
- Root cause in under 5 minutes at 94% accuracy, posted where your team works
Prevent
See the slow path before it pages
NeuBird compares span durations and error rates across services over time and flags dependencies whose latency is climbing 30 to 60 minutes before an alert on the user-facing service would fire.
- Flags dependencies whose span durations are trending up
- Surfaces services that emit no spans, so a trace stops partway
- Recommends missing SLOs for the services Tempo already traces
Operate
Keep the trace data useful
NeuBird reviews which services and span attributes show up in your traces and recommends where instrumentation is thin or inconsistent, so the next investigation has a complete path to follow.
- Identifies services with missing or inconsistent span attributes
- Spots recurring slow paths across incidents
- Remembers every verified fix, with no bulk telemetry stored
Better Together
Grafana Tempo + NeuBird
| Capability | Grafana Tempo | NeuBird |
|---|---|---|
| Distributed trace storage at scale | ✓ | Reads it in place |
| TraceQL search across spans and attributes | ✓ | Runs it during each investigation |
| Correlation with metrics, logs, Kubernetes and code changes | Through Grafana | 15+ sources in parallel |
| Root cause with cited evidence | Trace view | Under 5 minutes, 94% accuracy |
| Staged fix or rollback | Not in scope | Behind configurable human approval gates |
| Memory of past fixes | Not in scope | Verified fixes, no bulk telemetry stored |
Ecosystem
Works across your entire stack
Grafana Tempo is one piece of the picture. NeuBird queries it in place and correlates it with every other connected tool, and every agent in the center inherits the connection.
Observability
- Grafana
- Prometheus
- Grafana Loki
- OpenTelemetry
Infrastructure
- Kubernetes
- AWS
- Google Cloud
- Microsoft Azure
Incident management
- PagerDuty
- Opsgenie
- incident.io
Code and change
- GitHub
- GitLab
- Argo Workflows
FAQ
Common questions
How does NeuBird connect to Grafana Tempo?
You enter your Tempo query endpoint in NeuBird and, if the endpoint needs authentication, a dedicated credential sent as HTTP Basic auth. A Tempo that is only reachable inside your network can be published as a Teleport application instead. NeuBird queries the Tempo HTTP API at investigation time and stores no bulk telemetry.
What Grafana Tempo data does NeuBird use?
Distributed traces: the spans, services, attributes, durations and error status Tempo holds for the time range of an investigation.
Does NeuBird change anything in Grafana Tempo?
NeuBird uses Tempo as an investigation source. Any fix it proposes is staged for approval through the Suggest, Recommend, Act policy dial, set per action, with configurable human approval gates.
Is NeuBird a replacement for Grafana Tempo?
No. Tempo keeps storing and serving your traces. NeuBird is the AI SRE that investigates what those traces show, alongside every other tool you connect.
Get Started
Connect Grafana Tempo to the center.
Grafana Tempo gives you the data. Connect it to NeuBird once, and every agent that touches production inherits it, including the ones you build yourself.
