Classification AI tasks
Zero-shot classification — sync values, write descriptions, set the workflow.
Classification AI tasks
A classification task lets Runtime set a ticket attribute — for example queue, priority, or a dropdown DynamicField. The AI is zero-shot: you sync target values from the ticket system, write short descriptions, and the local LLM picks the matching value.
Create a task
- Open AI Tasks.
- Click + New AI task (empty draft) or Example classification (demo
with
OTAIBeispielAbteilung). - Studio opens the new task detail page (starts Inactive).
Target and LLM
On the right under AI Task settings:
- Prediction target — Queue, Priority, Service, Type, or DynamicField.
- For DynamicField: DynamicField name (exact name in the ticket system).
- LLM size — Studio recommends a size; the concrete model name appears below.
Sync values and describe them
- Click Sync values from ticket system. Studio pulls exact names from the ticket system (existing AI descriptions are never overwritten).
- Click a value and add an AI description — short, in the language of your tickets, when that value applies.
- Don’t predict marks values the AI must never choose (for example a raw inbox queue).
- Remove drops a value from the task (not from the ticket system).
Without useful descriptions, classification stays weak. Names must match the ticket system — no free-typed spelling variants.
Workflow settings
Under Workflow settings you control when Runtime runs and what happens on uncertain predictions. Save with Save workflow settings.
| Setting | Meaning |
|---|---|
| Only when state is | Optional: only tickets in this state (e.g. new) |
| Only when … is | Optional: only when the target attribute has a specific value |
| Also run when … is empty | Also run when the attribute is empty |
| Strictness | Minimum AI confidence: Lax (60%), Normal (80%), or Strict (90%) |
| Set a fallback value? | Write a safe replacement instead of the AI prediction when confidence is too low |
| Fallback value | Select the replacement; shown only when a fallback is enabled |
| Flag for human review? | Mark uncertain tickets for agents through the HumanReviewNeeded DynamicFields |
Set Strictness first. Then choose what happens when confidence is too low. Without a fallback value, human review stays enabled so no uncertain ticket is left without an action.
Under Advanced (optional): custom Base prompt, Write article note
with template placeholders ({result_value}, {confidence}, …).
Tickets that already have a confidence DynamicField for this attribute are not classified again.
Activate
- Set at least one eligibility filter (state and/or attribute / “empty”).
- No blocking values: Predict must not be on for values missing from the ticket system — otherwise Activate is blocked.
- Activate — Runtime picks up the task.
- Deactivate stops execution; the config remains.
Archive hides the task from the list without deleting it.
Tips
- Typically one active task per attribute (for example one queue task).
- After queue/priority changes in the ticket system, run Sync again.
- Check impact and fallbacks on the Dashboard.