Available

Classifier templates

Ready-made decisions you can call by id or copy and edit.

Use a template directly with {"template": "<id>", "input": ...}, or copy it into a saved decision to customize it.

Email triage

Sort incoming email into sales, support, billing, spam or newsletter, and flag urgent messages. email-triage

Output	Type	Values
`category`	choice	sales, support, billing, spam, newsletter, other
`urgent`	boolean	true / false

Decide whether an inbound lead is qualified, score its fit, and tag industry and buying intent. lead-qualification

Output	Type	Values
`qualified`	boolean	true / false
`fit_score`	score	No fit: personal use or unrelated need → Weak fit: small need, unclear budget → Moderate fit: real need, small team → Good fit: clear need, growing team → Excellent fit: urgent need, established company
`industry`	choice	software, ecommerce, finance, healthcare, agency, other
`intent`	choice	buy_now, evaluating, researching, none

Route website contact form submissions to sales, support, partnerships or hiring, and drop spam. contact-form-routing

Output	Type	Values
`route`	choice	sales, support, partnership, job_application, spam

Categorize support tickets, score urgency and sentiment, and flag tickets that need escalation. support-triage

Output	Type	Values
`category`	choice	bug, billing, account, how_to, feature_request, other
`urgency`	score	Low: a question or cosmetic issue → Medium: degraded experience with a workaround → High: core feature broken, no workaround → Critical: outage, data loss or security issue
`sentiment`	score	Angry → Frustrated → Neutral → Positive
`escalate`	boolean	true / false

Check an AI agent's proposed action before it runs: allow it, block it, or send it to a human. agent-action-guardrail

Output	Type	Values
`verdict`	choice	allow, review, reject
`risk`	score	None → Low → Medium → High → Severe

Identify what kind of document a text is before routing it to the right workflow. document-classification

Output	Type	Values
`document_type`	choice	invoice, receipt, contract, resume, purchase_order, other

A single yes/no gate for any message: is it spam? spam-detection

Output	Type	Values
`is_spam`	boolean	true / false