---
title: "Classify what a support ticket is asking for"
method: POST
path: "/v1/ai/chat/software-support-intent"
tags: ["chat:software-support-intent"]
---

# Classify what a support ticket is asking for

`POST /v1/ai/chat/software-support-intent`

## Request

- Base URL: `https://api.intura.co` (the document declares no server; this is the origin it was published from)
- URL: `https://api.intura.co/v1/ai/chat/software-support-intent`
- Auth: none declared

## Request body

- ModulesV1AiChatSoftwareSupportIntentSchemasClassifyRequest: One support message to classify. `message` is required.
  - `message` string, required: The ticket as it arrived — an in-app chat widget, an email to support@, a WhatsApp message, a help-centre form, an app-store review. Send the whole thing, log paste included: the ceiling is generous for exactly that reason. Bounded by the module's MAX_CHARS.
  - `history` string[], nullable: Previous turns in the conversation, oldest first. The last 4 are read. Worth sending on a reply: 'masih belum bisa' is a bug report if a crash was being discussed and a billing ticket if a failed charge was.
  - `channel` string, nullable: Where the ticket arrived — `widget`, `email`, `whatsapp`, `form`, `app_store`, `github`. Recorded, not scored: the corpus keeps it beside the text rather than in it, so no model reads it and it never moves a class. Send it so your own logs carry it.
  - `thresholds` object, nullable: Move the routing check for this one call: `route` (default 0.8), the probability the top class must clear, and `margin` (default 0.1), the lead it must hold over the runner-up. Either alone is fine; the other keeps Intura's default.

## Response `200`

Successful Response

- ModulesV1AiChatSoftwareSupportIntentSchemasClassifyResponse
  - `status` string: Always `success` on a 2xx
  - `code` integer: Mirrors the HTTP status code
  - `data` ModulesV1AiChatSoftwareSupportIntentSchemasClassifyResponseData, required: `data` for POST /v1/ai/chat/software-support-intent.
    - `label` string, required: `bug_report`, `feature_request`, `account_or_access`, `billing_or_subscription`, or `other`. Always `other` when `result.action` is `escalate`.
    - `score` number, required: The number this endpoint measured and decided on, 0..1, rounded to 4 dp — P(injection), P(scam), how strongly the frame reads as the card. Compare it against `thresholds` and you have `label`. This is the only number to threshold on; what it means on a given route is documented there.
    - `thresholds` object: The cuts this answer was decided by, after your saved settings and anything sent in `thresholds` on the request. Published on every response so a verdict can be compared with an older one: a score means nothing without the bar it was held to. Empty on an endpoint with nothing to tune.
    - `result` ModulesV1AiChatSoftwareSupportIntentSchemasClassifyResultData: `result` for a classification call: the spread, the check, and what to do.
      - `action` string, required: `route` — the class cleared both halves of the check (`thresholds.route` and `thresholds.margin`) and the ticket can be filed in that queue. `escalate` — it did not; send this one to a larger model or a human triager. This is the field to branch on.
      - `scores` object, required: Per-class numbers. Probability mass summing to 1 when a trained model answered; when the phrase layer answered — a deployment without the weights, or `model` asked for by name — it is evidence per class and sums to less. `model` says which ran. Every class in `labels` appears either way, including the ones at zero.
      - `candidate` string, required: The class the model preferred, before the confidence check. Equal to `label` when `action` is `route`. Returned for logging and threshold tuning — never file on it.
      - `margin` number, required: Gap between the top class and the runner-up. The second half of the check: a top class that barely leads is a coin flip however high it scored. It had to be at least `thresholds.margin`.
      - `handling` string, required: One line describing what this class means and which queue resolves it. Written for whoever is wiring the triage.
      - `history_used` integer, required: How many previous turns were actually read. Two verdicts with different values here did not see the same evidence.
      - `languages` string[], required: The languages this ticket was read in: one trained model per language. Every supported language when none could be identified.

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/intura/apis/intura-ai-api.md) - [All operations](https://skmtc.dev/intura/apis/intura-ai-api/llms.txt) - [OpenAPI document](https://skmtc.dev/intura/apis/intura-ai-api/revisions/7cb6af4c6390?raw)