WELLNESS INTELLIGENCE

Generally available

Turn "I'm fine, just tired" into a signal your product can act on.

200 wellbeing labels across 41 languages - sleep, stress, coping, help-seeking, habit adherence - each returned with the configuration ID and receipt you need to reproduce the call. No generative model is used to produce classifications.

Try Wellness Intelligence in the Playground Talk to Solutions Engineering

200 labels · 4 signal groups · 41 languages · p95 target <500ms · No generative model is used to produce classifications

detection result

stress_balance

workload_pressurevery high

sleep_quality_poorvery high

LanguageEN

Configurationsqcfg_WJ0XM1NX

Fingerprintfp_a3f8…e2

Re-run with the same pinned version → identical result

What this analyzer does and doesn't do

Detect 200 labeled wellbeing and behavioral signals in user text
Return confidence-ranked signals your product can route on
Cover 41 languages

✕Diagnose mental-health or clinical conditions
✕Infer how a user actually feels - it classifies the text
✕Provide medical or therapeutic advice
✕Replace your coaches, clinicians, or support staff

Sentiqra returns structured signals. Your policy, reviewers, and models make the decision. See the full boundary statement →

WHAT YOU'LL DETECT

Not "sentiment: negative". The specific wellbeing signal - with the label your program already knows.

Stress & Life Balance

overload_expression

“I can’t keep up with everything right now” → very high

Sleep & Recovery

sleep_quality_poor

“Third night in a row I barely slept” → very high

Support & Help-Seeking

professional_support_interest

“I’ve been thinking about talking to someone professional” → very high

Cognitive Load & Mental Strain

rumination_expression

Detected - example withheld

Social Connection & Belonging

loneliness_expression

Detected - example withheld

Browse all 200 labels in 4 signal groups

200 indicators across 4 signal groups - covering 41 languages.

Same deterministic product contract as every Sentiqra analyzer: pinned configuration, signed receipt, replayable results. Per-language benchmark publication is pending for this analyzer - evaluate it on your own labeled workload; the published methodology applies when results ship.

p95 latency target <500ms No generative model is used to produce classifications Every run tied to a config ID

See benchmarks and methodology

WHERE IT GETS USED

Three jobs this analyzer does well.

Wellbeing check-in triage for coaching products

A coaching app runs every check-in through Wellness Intelligence. sleep_quality_poor, workload_pressure, and energy_low route the user to the right program module - recovery content for poor sleep, workload tools for stress - instead of a generic daily tip.

Fit signals: daily check-ins · program personalization · multilingual user base

Help-seeking escalation before crisis

professional_support_interest and trusted_person_outreach signals escalate to a human coach or care pathway while the user is still reaching out - not after disengagement. Every escalation carries a replayable receipt showing exactly which language triggered it.

Fit signals: duty of care · human escalation paths · audit trail required

Habit and adherence personalization

workout_skipped, streak_break, and motivation_low tell a fitness app when a user is slipping before they churn. The nudge adapts to the detected signal - encouragement for low motivation, a lighter plan for overload.

Fit signals: retention pressure · adaptive nudges · habit-tracking products

Send text. Get ranked labels + a receipt you can replay.

request

POST /v1/analyze
Authorization: Bearer sq_live_your_api_key_here

{
  "text": "Haven't slept properly in days, work is crushing me, and I skipped the gym again this week.",
  "language": "en",
  "analyzers": ["wellness"]
}

response

{
  "language": "en",
  "signals": [
    { "analyzer": "wellness", "code": "physical_health", "label": "Physical Health", "score": 0.9, "confidence": "very_high", "level": "category" },
    { "analyzer": "wellness", "code": "sleep_quality_poor", "label": "Poor sleep quality", "score": 0.9, "confidence": "very_high", "level": "label", "parent": "physical_health" },
    { "analyzer": "wellness", "code": "difficulty_falling_asleep", "label": "Difficulty falling asleep", "score": 0.9, "confidence": "very_high", "level": "label", "parent": "physical_health" }
  ],
  "meta": { "analyzers": [{ "name": "wellness", "status": "completed", "signal_count": 3, "billed": true }], "partial": false },
  "usage": { "analyzer_runs": 1, "billed": true },
  "verification": {
    "configuration": "sqcfg_WJ0XM1NX",
    "fingerprint": "fp_8a72...19f",
    "input_commitment": "ic_31bd...a42",
    "signature": "sig_ed25519_4c1f...e2a"
  }
}

Full API reference

READING THE OUTPUT

What a Wellness Intelligence result tells you - and what it doesn't.

Intended task

Turn check-in and journal text into documented wellbeing signals - sleep, stress, coping, help-seeking - that a wellness product can route on.

Input requirements

text - the only field analyzed; up to 4,096 Unicode code points. Over the limit is rejected with input_too_long, never truncated.
language - must be a language this analyzer supports. Unsupported codes are rejected with 400 unsupported_language, never analyzed as a different language.
analyzers - include "wellness"; up to 2 analyzers per request, one billed run each.
No context beyond text - no user IDs, history, profiles, or attachments are read or inferred.
Very short check-ins carry little signal - "tired" alone can return a weak or empty result.

Ordinary positive

“I have slept badly three nights running and keep skipping meals - I feel completely drained.”

sleep_recovery very high

stress_balance high

nutrition_hydration medium

Safe inference: The check-in touches sleep, stress, and nutrition - enough to route a recovery-focused suggestion rather than a generic tip.

Confusing negative · Insufficient context

“My doctor said my results were normal but I still feel exhausted.”

What happens: Wellbeing signals can fire on the fatigue language - but the text also mentions a clinical finding the analyzer cannot evaluate. The signal describes wellbeing language in the text; it does not weigh medical content.

Why it's tricky: Wellness text often brushes against clinical claims. A sleep or stress signal is a content-routing hint - it is never a diagnosis, and concerning content should follow your own escalation policy rather than the signal alone.

What you can safely infer

Which documented wellbeing topics the text touches, and at what strength.
That results are reproducible - the same check-in on the same pinned configuration returns the same signals.

What you must not infer

✕A diagnosis or clinical status - wellness signals are not medical assessment.
✕That a user is at risk, or safe - escalation decisions belong to your own safety policy and human review.
✕That flat or empty results mean the user is well - thin text is thin evidence, not a clean bill of health.

Boundary: Wellness signals are not diagnoses. They describe wellbeing language in the text for product routing - suggestions, check-ins, content matching - never a clinical assessment.

Signal reference Evaluation evidence Understanding signals API reference Evaluate on your data

Wellness Intelligence is on every plan. Even Free.

Free

5,000 runs/mo

Build

$149/mo · 50,000 runs/mo

Growth

$349/mo · 150,000 runs/mo

Production

$799/mo · 500,000 runs/mo

Scale

$2,999/mo · 2,500,000 runs/mo

Enterprise

By agreement · SOC 2 Type II in progress

See full pricing and rate limits

Deterministic by construction, provable by receipt.

A signed verification receipt - configuration ID (sqcfg_...), result fingerprint (fp2_...), input commitment (ic3_...), and Ed25519 signature (sig_ed25519_...) - ships with every successful analysis result. Pin it to the stored decision and a later replay under the same supported configuration and output profile yields the identical canonical result - the difference between "the model said so" and evidence.

Verify a receipt

Where it fits in your pipeline

USER CHECK-INS ↓ WELLNESS INTELLIGENCE ↓

Stress & Balancevery high

Sleep & Recoveryvery high

Help-Seekingvery high

↓ YOUR POLICY ↓ Personalize · Nudge · Coach · Escalate

Often paired with: Emotion Analysis for fine-grained emotional states, Customer Service Intelligence for support interactions, Trust & Safety for harmful-content screening.

Used in: Customer Support Intelligence and Emotion & Escalation

Try it on your real check-in language.

Try Wellness Intelligence in the Playground Talk to Solutions Engineering

5,000 analyzer runs/month · No card required

Analyzer FAQ

New to Sentiqra? It's a deterministic text-analysis API - you send text, you get labeled, confidence-scored signals plus a replayable receipt. Wellness Intelligence is the wellness & behavioral signal detection analyzer.

What does Wellness Intelligence detect?

Detect wellbeing, behavioral, and human-state signals in multilingual text.

Which languages does it cover?

41 supported languages. Per-language benchmark publication is pending for this analyzer - evaluate it on your own labeled workload before relying on a specific language. Coverage is per-analyzer, not platform-wide.

How do I call it?

POST /v1/analyze with "analyzers": ["wellness"]. Same endpoint, auth, and response shape as every other analyzer - you can pair it with one more analyzer in the same request.

What does a call cost?

One analyzer run per call, billed against your plan's included runs (overage per plan). All GA analyzers are on every plan, including Free - see pricing.

How do I evaluate it on my data?

Label a few hundred of your own examples, run them through the free tier, and compare our signals to your labels. The evaluation playbook walks through building that test set - it's the same method we use internally.