ML deployment

Training has to be finished. A model still in Training queue has no key button.

Steps

1. Open your model

1. Data Intelligence → Machine Learning → the model name, or open it from Training queue.
2. You are on /ml/{model-id} with metrics and tabs.

2. Save to inventory (if prompted)

After training completes, click Save Model if the wizard prompts you: adds the model to your inventory list.

3. Generate API key

1. At the top of the model page, click Generate API key.
2. Copy the key on that screen. It is not shown again. Generating a new key replaces the old one.

4. Get integration details

1. Open the API Integration tab on the same page.
2. Copy the predict endpoint URL, headers, and sample payloads.

→ API integration guide

Test from the app

Use the in-app predict/test UI on the model page. Calls appear in the Usage section with channel Heimdall UI.

Monitor after deploy

What	Where
Account-wide charts	Sidebar → Usage → Data Intelligence
This model's request log	Model page → Usage section
Platform outages	/health

→ ML monitoring · Production monitoring

Common mistakes

Mistake	Fix
No API key button	Training may still be pending: check Training queue
404 Invalid API Key	Use this model's key, not the Read/Vision key
No usage data	Deploy key first; external calls need the key in headers

Next steps

• API integration guide
• Production best practices
• User journeys: full path from CSV to here