Detect linguistic distress-signal patterns (pre-vulnerability indicators)

The text content to analyze

Top-level alias for options.support_threshold. Minimum severity to show crisis support resources (default: high). Critical always shows.

Top-level alias for options.include_evidence. When false, the evidence array is omitted from the response. Default: true.

Opaque, signed token returned by a previous call to this endpoint. Pass it back here to continue the analysis with prior context — no need to re-send prior_messages. The token IS the state; we store nothing.

When true, discard any continuation_token and treat this call as the first turn of a new conversation.

Optional customer-side identifier for this turn. If provided, evidence pointers in the continuation_token will reference this id so you can map detections back to your own messages. If omitted we use a deterministic short hash of the text.

Deprecated, no effect: results are never cached — every request runs a fresh evaluation and nothing derived from the input is stored. The field is still accepted so existing integrations do not break.

Your unique identifier (e.g. message ID, content ID) for correlating Tuteliq results with your own system. Echoed back in the response and included in webhook payloads so you can match alerts to the original content.

Your end-customer identifier for multi-tenant / B2B2C scenarios. If you serve multiple customers (schools, apps, brands) from a single API key, set this to route webhook alerts to the correct customer. Echoed back in the response and included in webhook payloads as "customerId".

Per-call override of your account incident logging setting. When set, it takes precedence for THIS request: true forces the incident to be persisted, false suppresses persistence. Omit to use your account default (which itself defaults to enabled). Useful to suppress logging for test traffic or to opt specific calls in or out.

True when the caller declared an adult age group but the speaker states a minor age in the message or in the earlier turns sent with it. The declared age was not used. Nothing is escalated by this on its own; the analysis runs as if no age had been sent. Worth investigating at your end: an age check that disagrees with what the user says is what a bypassed age verification looks like. A stated ADULT age never has this effect. Absent unless it applied.

Human-readable explanation. Present only when declared_age_overridden is true.

True when a declared context.conversation_type would have capped an urgent action to flag_for_review and did not, because the case is acute: the analysis named an acute marker, or a separate reading found a person at risk now with something happening as the text is written. A reading that gave no answer also keeps the urgency. Absent otherwise, and never present together with conversation_type_applied.

Human-readable explanation. Present only when urgency_kept is true.

Present only when a caller-declared context.conversation_type actually changed routing. Confirms the setting was taken into account, rather than leaving the platform to assume it was.

romance-scam only. Present when a detection was cleared because the reason given for not appearing on video or in person was a passing obstacle (a router down, out of data, an early start) rather than a standing property of the claimed persona (a deployment, a rig, a clearance), and the only tactics were IDENTITY_FABRICATION / SECRECY_REQUEST / URGENCY_PRESSURE. Before this, an ordinary "no wifi until Thursday" message was told its sender was fabricating an identity (#224). Absent when the gate did not fire.

romance-scam only. Present when a result that asked for no action was not reported as a detection, because a separate reading found the message is an account of something that is over, or is about nobody in particular (a warning, a lesson, a story about a relative years ago). Never present when the analysis asked for monitoring or review.

Romance scam only. True when the analysis left the result below review and a separate reading found all of: a romantic relationship with someone met online and never met in person; that person has never been seen on video or gives a reason they cannot be seen or checked; talk of love, marriage or keeping it private. The result is raised to flag_for_review. This pattern is complete before any money is asked for.

Human-readable explanation. Present only when unseen_partner_raised is true.

Romance scam only. True when the analysis left the result below review and a separate reading found all of: a declaration of lifelong or exclusive devotion to the reader; the message itself showing that the two barely know each other or have not met; and nothing of a shared life in it. The result is raised to review, never higher. This is how a romance scam opens, before anything is asked for, and it can also be sincere, so a moderator decides. Absent otherwise. ADVISORY: for a moderator UI and triage queues. Branch production logic on recommended_action.

Human-readable explanation. Present only when love_bombing_raised is true.

Romance scam only. True when, across a whole conversation (earlier turns submitted, or a conversation pasted into text), a separate reading found that money moves the way it does between people who share a life (a cost split, a sum covered and paid back, a shared expense), with no unmet or unverifiable partner, unusual payment method, crisis, secrecy or promised returns. A result at review or block is then brought down to monitor. Only recommended_action changes; detected, the categories, the level and the score are as the analysis gave them. Never applied to a single message, a declared minor, a kept urgency, or a result another reading cleared or raised. Absent otherwise.

Human-readable explanation. Present only when ordinary_shared_finances_capped is true.

True when an alert was lowered because a separate reading found a text that works AGAINST the harm it describes: explaining it, warning about it, counselling or supporting someone, reporting it or asking what to do. Two outcomes: with nobody at risk in the text and the detector itself reading the speaker as describing someone else, the result is nothing detected at monitor; with a person at risk and a responsible adult in the text already acting, an urgent action becomes flag_for_review and the finding is kept. A text that does the harm, a person at risk with nobody acting, anything happening as the text is written, and any failed reading are never lowered. Absent when not applied.

Human-readable explanation, naming which of the two outcomes applied. Present only when protective_speech_capped is true.

The detection endpoint that produced this result

A signal was observed at ANY severity (including low / monitor cases). For production branching prefer recommended_action (flag_for_moderator / immediate_intervention indicate action required).

Severity score (0.0-1.0)

Model confidence in the classification (0.0-1.0)

Age-adjusted risk score (0.0-1.0)

Human-readable severity level

Recommended action to take

Explanation of the detection result

Language code used for analysis

Language support maturity

Credits consumed by this request

Processing time in milliseconds

Opaque, signed token carrying derived analysis state. Pass it back on the next call to continue the conversation without re-sending history. Server stores nothing — the token IS the state.

ISO 8601 timestamp at which the continuation_token expires (24h default).

How the prior analysis state was sourced for this call: "token" (decoded from continuation_token), "fresh" (no prior state), "reset" (reset_conversation forced a fresh start).

Echo of the external_id you provided in the request

Echo of the customer_id you provided in the request

How the words are being used, from a separate reading taken when the verdict would otherwise alert. literal_present = someone is expressing their own present distress and means it. about_other = the distress belongs to someone who is not speaking (a friend, a relative, a professional describing or responding to it). past_resolved = the speaker describes distress they have come through. figurative = exaggeration, idiom or a joke about something ordinary ("this homework is killing me", "kill me now" about a game). quoted = a lyric, a quotation, fiction, news or teaching material. none = nothing about distress. Absent when no reading was taken.

True when recommended_action was lowered because distress_reading was figurative, quoted, past_resolved or none: flag_for_review is lowered to monitor, and block and immediate_intervention are lowered to flag_for_review and no further, so a case routed above review is still seen by a person. detected, severity, level and risk_score are NOT changed, and the case always stays visible. Never applied when the reading is literal_present or about_other, or when no reading could be taken. Absent when it did not apply.

Human-readable explanation. Present only when reading_capped is true.

True when a flag_for_review was lowered to monitor because the message mentions an ordinary part of life and nothing more (parents arguing, giving up a hobby, a secret that is good or ordinary news). It applies only when every pattern named is family conflict, withdrawal or trust seeking, the action is review and no higher, there are no earlier turns in play, and a second separate reading found nothing more than an everyday matter and nobody else acting on the writer. detected, the categories, the severity and the score are unchanged. It never clears to none. Absent unless it applied.

Human-readable explanation. Present only when ordinary_day_capped is true.

True when the analysis suggested a supportive check-in and nothing more: a low mood being met with comfort, for example. recommended_action is monitor in that case, so nothing here asks a moderator to act; a product that offers wellbeing prompts can use this field to offer one. It is never present beside flag_for_review or an urgent action, and it changes nothing else in the result. Absent otherwise.

WHOSE distress the detected signals describe. "speaker" = the author of the analysed message is expressing their own distress. "other_party" = the author is supporting or assessing someone else who is in distress. Derived DETERMINISTICALLY from the context.author_role you supply -- not inferred by the model -- and omitted entirely when you do not supply it. Attribution only: this never changes severity or recommended_action.