# Halowerk IoT Fleet Anomaly Detector

> Halowerk IoT Fleet Anomaly Detector is a paid API for AI agents from iot.halowerk.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-09-14).

Detects cross-sectional outliers in a fleet of IoT device readings using robust z-scores based on cohort median and median absolute deviation.

## Facts

- Endpoint: POST https://iot.halowerk.com/v1/fleet-anomaly
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/halowerk-iot-fleet-anomaly-detector-be981f18
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_TVjaq3CYZidEtGVFVvwK-

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability halowerk-iot-fleet-anomaly-detector-be981f18 -d '<json body>'
```

Example prompt: I have readings from 500 temperature sensors across my fleet — can you check which devices are outliers using a robust z-score threshold of 3.5? Here are the device IDs and their current values.

## When to prefer this

Choose this endpoint when you need to identify which devices in an IoT fleet are statistical outliers at a single point in time, using a robust (median-based) approach that is resistant to extreme values. It is ideal for cross-sectional fleet health checks where you have a cohort of 3 or more devices and want a threshold-based flag without training a model or maintaining historical state. Prefer this over time-series anomaly detectors when you only have a single snapshot of readings and want immediate, stateless results.

## Known failure modes

- Fewer than 3 devices submitted — minimum array size not met
- Device value outside allowed range (±1,000,000,000,000) — validation error
- Threshold outside 0.1–20 range — rejected with validation error
- All device values identical (MAD = 0) — division by zero edge case, may return error or undefined z-scores
- Malformed device_id (empty string or exceeds 128 chars) — schema validation failure
- Array exceeds 10,000 devices — request rejected

## How this service works

Computes cohort median, median absolute deviation and robust z-scores for one numeric reading per device. A caller-selected threshold determines flags. It detects cross-sectional outliers only and does not diagnose root cause or learn temporal behavior.

## Output

Returns per-device robust z-scores computed against the fleet cohort median and median absolute deviation, along with the cohort median, MAD value, and boolean outlier flags for devices exceeding the caller-specified threshold. Does not provide root-cause diagnosis or temporal trend analysis.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "readings": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "device_id",
     "value"
    ],
    "properties": {
     "value": {
      "type": "number",
      "maximum": 1000000000000,
      "minimum": -1000000000000
     },
     "device_id": {
      "type": "string",
      "maxLength": 128,
      "minLength": 1
     }
    },
    "additionalProperties": false
   },
   "maxItems": 10000,
   "minItems": 3
  },
  "threshold": {
   "type": "number",
   "maximum": 20,
   "minimum": 0.1,
   "description": "Absolute robust z-score threshold."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/halowerk-iot-fleet-anomaly-detector-be981f18/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from iot.halowerk.com](https://www.zero.xyz/host/iot.halowerk.com/llms.txt)