Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.vh3.ai/llms.txt

Use this file to discover all available pages before exploring further.

Sentinels Guide

Sentinels are VH3 AI’s proactive monitoring layer. They continuously analyse your operational data to detect emerging risks and growth opportunities — before they become entrenched problems or missed revenue. You discover SLA pain at month-end. The pattern was visible in week two. Sentinels close that gap.

How sentinels work

Every sentinel is a pure database read — a structured query against your knowledge graph that evaluates a specific operational signal against configurable thresholds. There is no AI cost at the detection layer; intelligence is used only if you choose to generate a narrative explanation of what was detected.
1

Detection

The sentinel query runs against your graph — looking for the pattern it’s designed to detect (e.g. repeat visits at a site exceeding threshold).
2

Scoring

Results are scored by severity. Each sentinel has a default threshold that determines what counts as a trigger vs. noise.
3

Delivery

Triggered results are available via the API, and can be routed to Slack, Teams, email, or WhatsApp via automation.

Configuration

Every sentinel supports these configuration parameters:
ParameterDescription
thresholdMinimum severity to trigger (higher = fewer, more critical results)
lookbackDaysHow far back to analyse (default varies by sentinel)
limitMaximum results to return
excludeFiltersExclude specific engineers, sites, or customers from results

Operational sentinels

Thirteen operational sentinels monitor for emerging risks across engineers, sites, customers, and SLAs:

Engineer performance slip

Detects engineers whose SLA punctuality or completion quality has degraded compared to their historical baseline. Catches problems early — before a pattern becomes a client complaint.

Site deterioration

Identifies sites where fault frequency or repeat visits are trending upward. Surfaces sites that may need a planned maintenance visit rather than continued reactive attendance.

SLA breach cluster

Finds concentrated SLA breaches — by geography, engineer, customer, or time period. Distinguishes between isolated misses and systemic problems.

Scheduling drift

Flags jobs where planned vs. actual timings are diverging — catch planning assumptions that no longer match reality.

Data quality issues

Surfaces anomalies in job records that may indicate extraction or ingestion problems — keep your intelligence layer clean.

Growth opportunity sentinels

Six growth sentinels surface revenue opportunities hiding in your operational history:

Dormant customer

Identifies customers with no recent job activity who previously had regular engagement — potential re-engagement or churn risk before they formally leave.

Overdue service interval

Flags equipment or sites that have passed their recommended service interval — maintenance contract upsell opportunities.

Single-service cross-sell

Finds customers using only one service line when your business offers multiple — cross-sell candidates with evidence of engagement.

Engineer-flagged follow-up

Surfaces jobs where engineers noted “follow up,” “recommend,” or “return visit” — quotes that should have happened but might have been missed.

Seasonal buying patterns

Identifies customers whose service rhythms suggest upcoming seasonal needs — proactive outreach before they call someone else.

Geographic upsell clusters

Finds neighbourhoods where one scheduled visit would make multiple nearby follow-ups economical — route density opportunities.

Automation

Sentinel results are most powerful when routed automatically. Common patterns:
  • Daily Slack digest — summary of all sentinel triggers posted to an ops channel each morning
  • Email alerts — critical sentinels (SLA breach cluster, site deterioration) sent to account managers immediately
  • Weekly report inclusion — sentinel results embedded in weekly operational reports
  • Case creation — high-severity triggers automatically create a case for follow-up
  • WhatsApp notifications — urgent alerts routed to field managers on the move
All of these are achievable via the VH3 AI n8n nodes (100+ pre-built templates) or direct API integration.

From reactive to continuous

Traditional reporting: someone spends Monday morning building a spreadsheet that’s already out of date by Tuesday. Sentinel-powered operations: patterns surface in their second week, not their second month. The intelligence writes itself.