← all services
virtual-assistant 12 endpoints
Endpoint-level X-ray over the last 48h — 18 API calls.
Endpoints are derived from the request logs and templatized (:id).
Click one for its Neo4j fan-out, traces, and logs (fetched live).
See the raw calls:
all API calls ·
failing (5xx) →
What it costs:
its bill · namespace tilda · requests vs use · its LLM calls · AI spend by org
error budget
healthy
99.90% derived · 0.0× burn
p95 vs normal
—
no baseline yet
last deploy
2d ago
automated ·
40d07ba1Neo4j footprint
312
1.1 per request · 2 slow
owner · on-call
Sambasiva Bandarupalli
backup Ahmed Aburaed · CODEOWNERS /data-science/
| Endpoint | Calls ▾ | Avg latency | Max | Err % |
|---|---|---|---|---|
| GET /api/v1/va/sse/stream | 3 | — | — | 0.0% |
| GET /api/v1/va/steer/:id | 3 | 143 ms | 286 ms | 0.0% |
| GET /api/v1/va/work-orders/:id/wo-activities/recent | 2 | 126 ms | 142 ms | 0.0% |
| POST /api/v1/va/sse/register | 2 | 50 ms | 59 ms | 0.0% |
| DELETE /api/v1/va/sse/register | 1 | 56 ms | 56 ms | 0.0% |
| GET /api/v1/va/work-orders/:id | 1 | 72 ms | 72 ms | 0.0% |
| GET /api/v1/va/work-orders/:id/wo-tasks | 1 | 56 ms | 56 ms | 0.0% |
| GET /api/v2/va/work-order-configs | 1 | 107 ms | 107 ms | 0.0% |
| GET /api/v2/va/work-order-configs/:id | 1 | 178 ms | 178 ms | 0.0% |
| PATCH /api/v1/va/steer/:id/reported | 1 | 107 ms | 107 ms | 0.0% |
| POST /api/v1/va/steer | 1 | 267 ms | 267 ms | 0.0% |
| POST /api/v1/va/steer/:id/approve | 1 | 5.78 s | 5.78 s | 0.0% |
Per-endpoint Neo4j fan-out (and N+1 detection) is one click away on each endpoint's Queries tab — fetched live by sampling that endpoint's recent traces.