INDICATOR REFERENCE
All indicators across 12 production analyzers
Complete reference of 2680 indicators across 109 groups in up to 41 languages. Each indicator has a stable slug and code for programmatic access.
Browse indicators by domain
POST /v1/analyze/trust-safety
Trust & Safety
View all 210 trust & safety indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/cybersecurity
Cybersecurity
View all 200 cybersecurity indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/crisis-intelligence
Crisis Intelligence
View all 650 crisis intelligence indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/finance
Market Intelligence
View all 200 market intelligence indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/disinformation
Disinformation Analysis
View all 200 disinformation analysis indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/discrimination
Discrimination Analysis
View all 200 discrimination analysis indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/emotions
Emotion Analysis
View all 20 emotion analysis indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/customer-service
Customer Service Intelligence
View all 200 customer service intelligence indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/insurance
Insurance Intelligence
View all 200 insurance intelligence indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/dating-safety
Dating Safety
View all 200 dating safety indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/fraud-scam
Fraud & Scam Detection
View all 200 fraud & scam detection indicators with slugs, codes, and group assignments.
Browse indicators →
POST /v1/analyze/wellness
Wellness Intelligence
View all 200 wellness intelligence indicators with slugs, codes, and group assignments.
Browse indicators →
All groups at a glance
Every group across all 12 production analyzers, with indicator counts and links to the full indicator reference.
profanity_obscenity
Profanity & Obscenity
10
insults_derogation
Insults & Derogation
10
harassment_targeting
Harassment & Targeting
10
bullying_exclusion
Bullying & Social Exclusion
10
hate_identity_attack
Hate & Identity Attack
10
identity_discrimination
Identity-Based Discrimination
10
dehumanization_exclusionary_harm
Dehumanization & Exclusionary Harm
10
threats_intimidation
Threats & Intimidation
10
incitement_violence
Incitement & Glorification of Violence
10
sexual_harassment_abuse
Sexual Harassment & Sexualized Abuse
10
coercive_controlling_abuse
Coercive & Controlling Abuse
10
self_harm_encouragement
Self-Harm & Suicide Encouragement
10
self_harm_ideation
Self-Harm & Suicidal Ideation
10
privacy_doxxing
Privacy Abuse & Doxxing
10
scams_fraud_impersonation
Scams, Fraud & Impersonation
10
spam_platform_abuse
Spam & Manipulative Platform Abuse
10
child_safety_predatory_language
Child Safety & Predatory Language
10
violent_extremism
Violent Extremism & Recruitment
10
dangerous_behavior_encouragement
Dangerous Behavior & Harm Encouragement
10
toxic_conflict
Toxic Conflict & Hostile Conversation
10
evasion_coded_abuse
Evasion & Coded Abuse
10
phishing_delivery
Phishing Delivery
20
access_identity
Access Identity
30
endpoint_malware
Endpoint Malware
50
network_lateral
Network Lateral
30
app_cloud_data
App Cloud Data
50
infra_intel
Infra Intel
20
action_coordination
Action Coordination
73
identity_emotion
Identity Emotion
107
info_dynamics
Info Dynamics
97
humanitarian_migration
Humanitarian Migration
83
governance
Governance
90
threat_conflict
Threat Conflict
116
influence_ops
Influence Ops
84
monetary_policy
Monetary Policy & Central Banks
10
macro_data_surprises
Macroeconomic Data & Surprise
10
fiscal_trade_policy
Fiscal, Trade & Government Policy
10
earnings_financial_results
Earnings & Financial Results
10
corporate_guidance_outlook
Corporate Guidance & Outlook
10
capital_returns_financing
Capital Returns & Financing
10
mergers_acquisitions
Mergers, Acquisitions & Strategic Transactions
10
management_key_people
Management & Key-Person Actions
10
ownership_activism_insiders
Ownership, Activism & Insider Actions
10
products_operations_contracts
Products, Operations & Major Contracts
10
regulatory_approval_ip
Regulatory Approval, Licensing & Intellectual Property
10
legal_investigations
Legal, Enforcement & Investigations
10
credit_liquidity_distress
Credit, Liquidity & Financial Distress
10
banking_systemic_risk
Banking & Systemic Financial Risk
10
supply_chain_commodities
Supply Chain, Commodities & Physical Disruption
10
geopolitical_security
Geopolitical & Security Events
10
sovereign_fx_policy
Sovereign, FX & External Financing
10
market_flows_positioning
Market Flows, Positioning & Market Structure
10
market_anomalies_trends
Market Anomalies & Emerging Trends
10
information_social_signals
Information Quality, Social Signals & News Novelty
10
info_fabrication
Info Fabrication
30
rumor_context
Rumor Context
30
source_evasion
Source Evasion
30
influence_persuasion
Influence Persuasion
50
political_conspiracy
Political Conspiracy
30
platform_coordination
Platform Coordination
30
conduct_bias
Conduct Bias
40
identity_origin
Identity Origin
30
identity_status
Identity Status
40
identity_personal
Identity Personal
30
context_access
Context Access
40
conduct_hostile
Conduct Hostile
20
joy
Joy
1
sadness
Sadness
1
anger
Anger
1
fear
Fear
1
surprise
Surprise
1
disgust
Disgust
1
love
Love
1
pride
Pride
1
shame
Shame
1
hope
Hope
1
access_account
Access Account
38
billing_retention
Billing Retention
25
product_tech
Product Tech
51
delivery_status
Delivery Status
24
escalation_urgency
Escalation Urgency
37
security_feedback
Security Feedback
25
claim_type
Claim Type
50
claim_fraud
Claim Fraud
60
claim_process
Claim Process
40
claim_details
Claim Details
50
deception_manipulation
Deception Manipulation
50
abuse_threats
Abuse Threats
50
sexual_boundaries
Sexual Boundaries
30
exploitation
Exploitation
30
platform_misc
Platform Misc
40
impersonation
Impersonation
50
payment_diversion
Payment Diversion
50
fake_invoice
Fake Invoice
50
social_engineering
Social Engineering
50
mental_emotional
Mental Emotional
60
physical_health
Physical Health
70
social_support
Social Support
20
tools_productivity
Tools Productivity
50
Reading any analyzer's signals
What a signal means
- ✓The submitted text matched the documented pattern for that
code- route it to the policy or queue that owns the label. - ✓Reproducibility - the same input on the same pinned configuration and output profile returns the same signals, and the receipt records which configuration produced them.
What a signal never means
- ✕Verification - a signal means the text describes something in documented language, not that the event, claim, or intent is real.
- ✕Clearance - a missing signal means "not detected," never "safe" or "compliant."
- ✕Authorial intent - quoted and reported speech can match the same patterns as first-person language.
Every analyzer page carries a domain-specific decision guide - intended task, input requirements, worked examples, and the exact inference boundary - linked from each reference below. Requests in a language an analyzer does not support are rejected with 400 unsupported_language, never analyzed as a different language.
Using indicators in API responses
When you call /v1/analyze, the response includes matched labels with signal-match scores. Each signal is identified by its code and includes a level field (“category” or “label”). A score expresses signal-match strength under a particular analyzer configuration. It is not a probability that the signal or a downstream action is correct. Validate action thresholds on representative labeled data.
{
"language": "en",
"language_source": "declared",
"signals": [
{
"analyzer": "trust-safety",
"code": "insults_derogation",
"label": "Insults & Derogation",
"score": 0.86,
"level": "category"
},
{
"analyzer": "trust-safety",
"code": "insult",
"label": "Insult",
"score": 0.99,
"level": "label",
"parent": "insults_derogation"
},
{
"analyzer": "trust-safety",
"code": "belittling",
"label": "Belittling",
"score": 0.99,
"level": "label",
"parent": "insults_derogation"
}
],
"meta": {
"analyzers": [
{
"name": "trust-safety",
"status": "completed",
"applicability": "analyzable",
"assessment": "signals_detected",
"signal_count": 3,
"billed": true
}
]
},
"usage": {
"analyzer_runs": 1,
"billed": true
},
"verification": {
"version": 3,
"configuration": "sqcfg_ZZW77NM9",
"fingerprint": "fp2_8a72c4...19f",
"input_commitment": "ic3_31bd5e...a42",
"signature": "sig_ed25519_4c1f...e2a",
"key_id": "edk_af4f218e",
"binding_key_id": "bk_31bd5e42f7a019c8"
}
}Quickstart Guide
First API call in under 5 minutes
API Reference
Full endpoint documentation
Benchmark Results
Per-language Top-3 Hit Rate
Pricing
From Free to Enterprise
Public Indicator Dictionary
Trust & Safety 210 indicators
Benchmark Methodology
How we measure Top-3 Hit Rate
Docs Overview
All documentation domains
Request access5,000 analyzer runs/month · No card required