# Real-time IoT anomaly detection with MQTT and OpenAI: n8n workflow

> Started by a clock, and works across Email, Postgres and Slack. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/real-time-iot-anomaly-detection-with-mqtt-and-openai (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Alerts and monitoring](https://millionrounds.com/workflows?category=Alerts+and+monitoring#library)

# Real-time IoT anomaly detection with MQTT and OpenAI

Started by a clock, and works across Email, Postgres and Slack. It hands the judgement calls to OpenAI. 17 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Freal-time-iot-anomaly-detection-with-mqtt-and-openai)

**17 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 2 Model 2 Logic 6 Service 7

The steps in the order they run, from what starts it.

- 1 **MQTT Sensor Data Ingestion** Mqtt trigger *Starts it*
- 2 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 3 **Model Retraining Schedule** Schedule trigger *Starts it*
- 4 **Workflow Configuration** Set *Logic*
- 5 **AI Anomaly Detection Agent** Agent *Model*
- 6 **Fetch Historical Data for Retraining** Postgres *Service*
- 7 **Edge Preprocessing & Validation** Code *Logic*
- 8 **Check for Anomalies** If *Logic*
- 9 **Retrain ML Model via API** Http Request *Service*
- 10 **Normalize Sensor Data** Set *Logic*
- 11 **Store Anomaly Records** Postgres *Service*
- 12 **Store Raw Data in Time-Series DB** Postgres *Service*
- 13 **Send Alert to Dashboard API** Http Request *Service*
- 14 **Aggregate Sensor Readings** Aggregate *Logic*
- 15 **Send Slack Alert** Slack *Service*
- 16 **Statistical Anomaly Detection** Code *Logic*
- 17 **Send Email Alert** Email Send *Service*

## How it's built

- **Starts on:** A clock
- **Steps:** 17, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Email, Postgres, Slack
- **Model:** OpenAI

## Questions

What does it need to run?

An n8n account, plus your own Email, Postgres and Slack accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on a clock.

Does it use AI?

Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 17 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 17 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Freal-time-iot-anomaly-detection-with-mqtt-and-openai)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Email](https://millionrounds.com/workflows?service=Email#library)[Postgres](https://millionrounds.com/workflows?service=Postgres#library)[Slack](https://millionrounds.com/workflows?service=Slack#library)

## Workflows like it

Also alerts and monitoring, with the same services where possible, closest in size first.

- [**AI Qwen-Vl-Plus powered car fleet maintenance alert system** 17 steps · calls a model · Postgres, Slack](https://millionrounds.com/workflow/ai-qwen-vl-plus-powered-car-fleet-maintenance-alert-system)
- [**Automate investment risk monitoring with Qwen-Max AI and Slack** 17 steps · calls a model · Gmail, Slack](https://millionrounds.com/workflow/automate-investment-risk-monitoring-with-qwen-max-ai-and-sla)
- [**Classify supplier tiers with Google Sheets and Groq** 17 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/classify-supplier-tiers-with-google-sheets-and-groq)
- [**Classify workflow errors with Claude and Slack** 17 steps · calls a model · Jira, Slack](https://millionrounds.com/workflow/classify-workflow-errors-with-claude-and-slack)
- [**Detect maverick spend and alert reviewers with Slack and Gmail** 17 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/detect-maverick-spend-and-alert-reviewers-with-slack-and-gma)
- [**Monitor AI infrastructure costs and route budget alerts** 17 steps · calls a model · Email, Slack](https://millionrounds.com/workflow/monitor-ai-infrastructure-costs-and-route-budget-alerts)