Azure Data Explorer with NeuBird, the AI SRE: KQL answers, not KQL homework
NeuBird writes and runs KQL against your Azure Data Explorer clusters during an investigation, then correlates the results 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
The right query, written for you
When an alert fires, NeuBird lists the databases the connection can see, writes KQL scoped to the affected service and time window, and runs it against the cluster. It sets the error spikes and log patterns it finds against your cloud, Kubernetes and deploy history, queried in parallel, and returns the causal chain with the queries attached.
- Scopes each KQL query to the service, table and time window in question
- Correlates Azure Data Explorer results with deploys and config changes
- Root cause in under 5 minutes at 94% accuracy, posted where your team works
Prevent
Trends in the data before they page
NeuBird queries the telemetry your clusters already hold for rising error rates and latency trends, and flags the services heading toward an incident 30 to 60 minutes before an alert would fire.
- Flags error and latency trends building in Azure Data Explorer tables
- Surfaces services that log to a cluster but have no alert on that data
- Recommends missing SLOs for the services your telemetry already describes
Operate
Recurring patterns, named
Between incidents, NeuBird looks back across past investigations for the log patterns and failure modes that keep returning, so your team can fix the cause once.
- Identifies recurring error signatures across clusters and databases
- Works with clusters in other tenants through one connection per cluster
- Remembers every verified fix, with no bulk telemetry stored
Better Together
Azure Data Explorer + NeuBird
| Capability | Azure Data Explorer | NeuBird |
|---|---|---|
| Fast analytics over log and telemetry data | ✓ | Queries it in place |
| Kusto Query Language (KQL) | ✓ | Writes and runs KQL for each investigation |
| Correlation with cloud, Kubernetes and code changes | Data you ingest | 15+ sources in parallel |
| Root cause with cited evidence | Query results | 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
Azure Data Explorer 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.
Cloud
- Microsoft Azure
- Azure Monitor
- AKS
- Kubernetes
Incident management
- PagerDuty
- ServiceNow
- Opsgenie
Collaboration
- Microsoft Teams
- Slack
Code and change
- Azure DevOps
- GitHub
- Jira
FAQ
Common questions
How does NeuBird connect to Azure Data Explorer?
You register a Microsoft Entra ID application, grant it Viewer access on the databases NeuBird should query, and enter the cluster URI, tenant ID and client ID in NeuBird. NeuBird authenticates with a client secret or with workload identity federation, and stores no bulk telemetry.
What Azure Data Explorer data does NeuBird use?
The log and telemetry data in the cluster’s databases, queried with KQL at investigation time. NeuBird sees the databases and tables the application’s role grants it.
Can NeuBird query more than one cluster?
Yes. Each connection addresses one cluster by its data-plane URI, so you add a connection per cluster, including clusters in other tenants or subscriptions. Connections can share the same Entra application.
Is NeuBird a replacement for Azure Data Explorer?
No. Azure Data Explorer keeps storing and serving your log and telemetry data. NeuBird is the AI SRE that queries it during an investigation, alongside every other tool you connect.
Get Started
Connect Azure Data Explorer to the center.
Azure Data Explorer gives you the data. Connect it to NeuBird once, and every agent that touches production inherits it, including the ones you build yourself.
