Configure Retell AI enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for Retell AI. Trigger with phrases like "retellai SSO", "retellai RBAC", "retellai enterprise", "retellai roles", "retellai permissions", "retellai SAML".
Installation
Details
Usage
After installing, this skill will be available to your AI coding assistant.
Verify installation:
skills listSkill Instructions
name: retellai-enterprise-rbac description: | Configure Retell AI enterprise SSO, role-based access control, and organization management. Use when implementing SSO integration, configuring role-based permissions, or setting up organization-level controls for Retell AI. Trigger with phrases like "retellai SSO", "retellai RBAC", "retellai enterprise", "retellai roles", "retellai permissions", "retellai SAML". allowed-tools: Read, Write, Edit version: 1.0.0 license: MIT author: Jeremy Longshore jeremy@intentsolutions.io
Retell AI Enterprise RBAC
Overview
Configure enterprise-grade access control for Retell AI integrations.
Prerequisites
- Retell AI Enterprise tier subscription
- Identity Provider (IdP) with SAML/OIDC support
- Understanding of role-based access patterns
- Audit logging infrastructure
Role Definitions
| Role | Permissions | Use Case |
|---|---|---|
| Admin | Full access | Platform administrators |
| Developer | Read/write, no delete | Active development |
| Viewer | Read-only | Stakeholders, auditors |
| Service | API access only | Automated systems |
Role Implementation
enum Retell AIRole {
Admin = 'admin',
Developer = 'developer',
Viewer = 'viewer',
Service = 'service',
}
interface Retell AIPermissions {
read: boolean;
write: boolean;
delete: boolean;
admin: boolean;
}
const ROLE_PERMISSIONS: Record<Retell AIRole, Retell AIPermissions> = {
admin: { read: true, write: true, delete: true, admin: true },
developer: { read: true, write: true, delete: false, admin: false },
viewer: { read: true, write: false, delete: false, admin: false },
service: { read: true, write: true, delete: false, admin: false },
};
function checkPermission(
role: Retell AIRole,
action: keyof Retell AIPermissions
): boolean {
return ROLE_PERMISSIONS[role][action];
}
SSO Integration
SAML Configuration
// Retell AI SAML setup
const samlConfig = {
entryPoint: 'https://idp.company.com/saml/sso',
issuer: 'https://retellai.com/saml/metadata',
cert: process.env.SAML_CERT,
callbackUrl: 'https://app.yourcompany.com/auth/retellai/callback',
};
// Map IdP groups to Retell AI roles
const groupRoleMapping: Record<string, Retell AIRole> = {
'Engineering': Retell AIRole.Developer,
'Platform-Admins': Retell AIRole.Admin,
'Data-Team': Retell AIRole.Viewer,
};
OAuth2/OIDC Integration
import { OAuth2Client } from '@retellai/sdk';
const oauthClient = new OAuth2Client({
clientId: process.env.RETELLAI_OAUTH_CLIENT_ID!,
clientSecret: process.env.RETELLAI_OAUTH_CLIENT_SECRET!,
redirectUri: 'https://app.yourcompany.com/auth/retellai/callback',
scopes: ['read', 'write'],
});
Organization Management
interface Retell AIOrganization {
id: string;
name: string;
ssoEnabled: boolean;
enforceSso: boolean;
allowedDomains: string[];
defaultRole: Retell AIRole;
}
async function createOrganization(
config: Retell AIOrganization
): Promise<void> {
await retellaiClient.organizations.create({
...config,
settings: {
sso: {
enabled: config.ssoEnabled,
enforced: config.enforceSso,
domains: config.allowedDomains,
},
},
});
}
Access Control Middleware
function requireRetell AIPermission(
requiredPermission: keyof Retell AIPermissions
) {
return async (req: Request, res: Response, next: NextFunction) => {
const user = req.user as { retellaiRole: Retell AIRole };
if (!checkPermission(user.retellaiRole, requiredPermission)) {
return res.status(403).json({
error: 'Forbidden',
message: `Missing permission: ${requiredPermission}`,
});
}
next();
};
}
// Usage
app.delete('/retellai/resource/:id',
requireRetell AIPermission('delete'),
deleteResourceHandler
);
Audit Trail
interface Retell AIAuditEntry {
timestamp: Date;
userId: string;
role: Retell AIRole;
action: string;
resource: string;
success: boolean;
ipAddress: string;
}
async function logRetell AIAccess(entry: Retell AIAuditEntry): Promise<void> {
await auditDb.insert(entry);
// Alert on suspicious activity
if (entry.action === 'delete' && !entry.success) {
await alertOnSuspiciousActivity(entry);
}
}
Instructions
Step 1: Define Roles
Map organizational roles to Retell AI permissions.
Step 2: Configure SSO
Set up SAML or OIDC integration with your IdP.
Step 3: Implement Middleware
Add permission checks to API endpoints.
Step 4: Enable Audit Logging
Track all access for compliance.
Output
- Role definitions implemented
- SSO integration configured
- Permission middleware active
- Audit trail enabled
Error Handling
| Issue | Cause | Solution |
|---|---|---|
| SSO login fails | Wrong callback URL | Verify IdP config |
| Permission denied | Missing role mapping | Update group mappings |
| Token expired | Short TTL | Refresh token logic |
| Audit gaps | Async logging failed | Check log pipeline |
Examples
Quick Permission Check
if (!checkPermission(user.role, 'write')) {
throw new ForbiddenError('Write permission required');
}
Resources
Next Steps
For major migrations, see retellai-migration-deep-dive.
More by jeremylongshore
View allOauth Callback Handler - Auto-activating skill for API Integration. Triggers on: oauth callback handler, oauth callback handler Part of the API Integration skill category.
Rabbitmq Queue Setup - Auto-activating skill for Backend Development. Triggers on: rabbitmq queue setup, rabbitmq queue setup Part of the Backend Development skill category.
evaluating-machine-learning-models: This skill allows Claude to evaluate machine learning models using a comprehensive suite of metrics. It should be used when the user requests model performance analysis, validation, or testing. Claude can use this skill to assess model accuracy, precision, recall, F1-score, and other relevant metrics. Trigger this skill when the user mentions "evaluate model", "model performance", "testing metrics", "validation results", or requests a comprehensive "model evaluation".
building-neural-networks: This skill allows Claude to construct and configure neural network architectures using the neural-network-builder plugin. It should be used when the user requests the creation of a new neural network, modification of an existing one, or assistance with defining the layers, parameters, and training process. The skill is triggered by requests involving terms like "build a neural network," "define network architecture," "configure layers," or specific mentions of neural network types (e.g., "CNN," "RNN," "transformer").
