AI Explain

Ask PulseBoard to explain a spike in any metric. The default in-process analyser (no external LLM, no data leaves your instance) uses mean, standard deviation and single-step jump detection to produce a deterministic, human-readable explanation.

API

POST /api/ai/explain
{
  "seriesName": "payments.latency.p99",
  "samples": [
    {"ts": 1, "value": 1.0},
    {"ts": 2, "value": 1.1},
    {"ts": 3, "value": 9.0},
    {"ts": 4, "value": 1.1}
  ]
}
// → "Largest single-step jump was 7.90 at index 3 (> 2× stddev)..."

Pluggable provider

The default is a deterministic in-process analyser — your samples never leave the edge. Enterprise plans can configure a private LLM adapter (IAiProvider) to use OpenAI, Azure OpenAI, or any compatible API including a private deployment.

Where it shows up

• The "Explain spike" button on any timeseries panel.
• The alert detail drawer — auto-runs against the firing series.
• The /api/ai/explain endpoint for your own tooling.