Control what sensitive data each role can access through AI queries. 13 data domains, priority-based rules, full audit logging.
RBAC adjusts the risk score based on user role. The same query can be legitimate for HR but suspicious for a regular employee.
Adlibo does not manage your users. Your application sends role context via HTTP headers, and Prompt Guard uses this information to adjust its scoring. RBAC is NOT included in DataShield.
X-User-Role: HR_MANAGERDefine your organization's roles and the data domains each role can access.
Your application adds HTTP headers (X-User-Role, X-User-Department) to each API request.
Prompt Guard automatically adjusts the risk score based on role and query.
The same query can be allowed for HR but blocked for a regular employee.
RBAC scoring considers the user's role to déterminé if a query is legitimate or suspicious.
Analyzed query
"Show me Jean Dupont's salary"
HR_MANAGEREMPLOYEEIT_ADMINRBAC is available in Business and Enterprise plans of Prompt Guard.
Your application sends the role via HTTP headers. Prompt Guard adjusts scoring based on context.
Automatic role sync from your IAM. Headers are injected automatically.
| Feature | Business | Enterprise |
|---|---|---|
| Data domains | 4 | 13 |
| Role patterns | Exact match | Wildcards (*) |
| IAM intégration | Headers HTTP | AD / Okta / LDAP |
| Audit trail | 30 days | 90+ days |
| SIEM intégration | - | Splunk, Elastic, Datadog |
Define precisely which data types each role can query through AI.
PII_DATAPersonal data
FINANCIAL_DATAFinancial data
HR_RECORDSHR records
CODE_ACCESSSource code
HEALTH_INFOHealth (HIPAA)
LEGAL_DOCSLégal docs
CLIENT_DATAClient data
CREDENTIALSCredentials
SECURITY_INFOSecurity info
SYSTEM_CONFIGSystem config
STRATEGIC_PLANSStrategic plans
COMMUNICATIONCommunications
RESEARCH_IPResearch IP
Business (4 domains)Enterprise only (9 domains)
Simply add HTTP headers to your existing API calls.
import { Adlibo } from '@adlibo/sdk';
const adlibo = new Adlibo('al_live_xxx');
// Add role context to your API calls
const result = await adlibo.analyze(userInput, {
headers: {
'X-User-Role': 'HR_MANAGER',
'X-User-Department': 'Human Resources',
'X-User-Groups': 'hr-team,payroll-access',
'X-User-Email': 'manager@company.com'
}
});
// Score is adjusted based on role context
if (result.safe) {
// HR can access salary data
await sendToLLM(userInput);
} else {
// Access denied based on role
console.log(`Blocked: ${result.severity}`);
console.log(`Risk Score: ${result.riskScore}`);
}Start with RBAC Basic in the Business plan, or contact us for RBAC Enterprise with full IAM intégration.