Skip to main content
AI Model Governance & Configuration provides enterprise organizations with comprehensive control over AI usage, credentials, and routing. These features enable administrators to implement security policies, manage costs, ensure compliance, and maintain centralized control over AI automation workflows.

​
What You Can Control

AI Model Access

Restrict which AI models organization members can use

Organization Credentials

Centrally manage API keys and authentication

AI Proxy Routing

Route AI requests through custom proxy URLs
Together, these features provide complete governance over AI usage within your organization while maintaining the flexibility and power of Gumloop’s automation platform.

​
AI Model Access Control

Control which AI models are available to your organization members with granular restrictions and automatic fallbacks.
Available at: gumloop.com/settings/organization/ai-model-access-control
AI Model Access Control Main Page

​
Core Capabilities

Configure either an allow list (only selected models available) or deny list (selected models blocked). Choose the approach that best fits your security and compliance requirements.
Select or deselect all models from specific AI providers at once. Quickly manage access across entire provider ecosystems like OpenAI, Anthropic, or Google.
When a restricted model is requested, the system automatically uses your designated fallback model. This ensures workflows continue running smoothly even when preferred models are unavailable.

​
Supported AI Providers

Model restrictions work across all integrated AI providers, including:
  • OpenAI (GPT models)
  • Anthropic (Claude models)
  • Google (Gemini models)
  • DeepSeek models
  • Azure OpenAI
  • Grok
  • And all other integrated providers

​
How to Configure Model Access

Enable Model Restrictions

Enable Model Restrictions
Toggle the “restrict models?” switch to enable access control. When first enabled, all models are selected by default (allow list mode).

Choose Your Control Mode

Allow List Mode (recommended for strict control)
  • Only selected models are available to members
  • Best for compliance-heavy organizations
  • Users can only access explicitly permitted models
Deny List Mode (recommended for targeted restrictions)
  • Selected models are blocked, all others available
  • Best for general access with specific exclusions
  • Ideal for cost control scenarios

Select Models by Provider

Model Selection by Provider
Browse models organized by AI provider. Use provider-level checkboxes to quickly select or deselect all models from a provider, or choose individual models for more granular control.

Configure Fallback Model

Fallback Model Configuration
The system automatically selects the first available model as your fallback. This model is used when a restricted model is requested, ensuring workflows continue to function without interruption.

​
Common Use Cases

  • Compliance
  • Performance
Meeting Regulatory Requirements
  • Enable allow list mode
  • Only permit models that meet data residency requirements
  • Block models that don’t comply with industry regulations (HIPAA, GDPR, etc.)
  • Document which models are approved for different data classifications

​
Organization Credentials

Centrally manage AI API keys at the organization level. When configured, these credentials automatically override personal and workspace credentials across your entire organization.
Available at: gumloop.com/settings/organization/credentials
Organization Credentials Main Page

​
How It Works

Organization credentials follow this hierarchy:
Organization credentials always take priority over both workspace and personal credentials. This ensures consistent billing, access control, and compliance across all workflows in your organization.

​
Supported Providers

ProviderAPI Key TypeWhat You Get
OpenAIAPI KeyAccess to GPT models and OpenAI services
AnthropicAPI KeyAccess to Claude models
PerplexityAPI KeyAccess to Perplexity AI models
XAIAPI KeyAccess to Grok models

​
Setup Process

Add New AI Credential

Add AI Organization Credential
Click “Add Credential” and select your AI provider (OpenAI, Anthropic, Perplexity, or XAI). Choose “API Key” as the credential type.

Configure Your API Key

Enter your organization’s API key for the selected provider. Configure any provider-specific settings as needed.
Keep your API keys secure. Never share them in documentation, code repositories, or public channels.

​
Key Benefits

Unified Access

All members automatically use organization API keys. No need for individual key management across teams.

Cost Control

Centralized billing for all AI usage. Track consumption across teams and simplify budget management.

Security

All AI calls use audited and compliant credentials. Maintain consistent security policies across workflows.

Governance

Prevent unauthorized AI usage through personal credentials. Ensure all usage goes through approved channels.

​
AI Proxy Routing

Route AI provider requests through custom proxy URLs to use your own infrastructure, implement security policies, or integrate with specialized AI gateways.

​
Core Features

Route all requests through organization-controlled proxy servers. Direct traffic through your own infrastructure for complete control over AI interactions.
Map Gumloop model names to custom proxy model identifiers. Use your own model naming conventions while maintaining compatibility with existing workflows.
Configure different proxies for different AI providers. Customize routing based on your infrastructure and compliance requirements.

​
Setup Process

Access Proxy Configuration

AI Proxy Routing Overview
Navigate to your organization credentials page, find your AI provider credential (OpenAI, Anthropic, etc.), and click “Configure Proxy”.
The “Configure Proxy” button only appears for AI provider credentials.

Set Your Proxy URL

Enter your custom proxy base URL (e.g., https://your-proxy.company.com). This URL will replace the default AI provider endpoint.
Your proxy URL must be accessible from Gumloop infrastructure.

Configure Model Mappings (Optional)

Model Name Mapping
Map Gumloop model names to your proxy-specific model identifiers. For example, map gpt-4 to custom-gpt-4-enterprise if your proxy uses non-standard model names.

​
Common Scenarios

  • Enterprise Gateway
  • Custom Models
  • Compliance
Corporate AI Management PlatformRoute through your corporate AI gateway for:
  • Centralized logging and monitoring
  • Unified cost tracking across all AI usage
  • Consistent security policies
  • Compliance with corporate standards

​
Configuration Examples

Proxy URL: https://ai-gateway.company.com/v1
Model Mappings: (none - use default model names)
Simple routing through your gateway without custom model names.
Proxy URL: https://custom-ai.company.com/api
Model Mappings:
  gpt-4 → company-gpt-4-tuned
  gpt-3.5-turbo → company-gpt-35-fast
  claude-3-opus → company-claude-opus
Map Gumloop model names to your organization’s custom model identifiers.
Proxy URL: https://eu-ai-proxy.company.com/v1
Model Mappings: (none - standard names with EU routing)
Route through EU infrastructure for GDPR compliance while using standard model names.

​
How These Features Work Together

When a workflow executes that requires AI, here’s what happens:
1

Model Selection

AI Model Access Control determines which models are available based on your allow/deny list configuration.
2

Credential Resolution

Organization Credentials provide authentication, overriding any workspace or personal credentials.
3

Request Routing

AI Proxy Routing determines the endpoint and applies any model name mappings before execution.
4

Execution

The request is sent through the configured proxy (if any) with organization credentials to the AI provider.

​
Security and Compliance

Access Control

All features require organization admin privileges to configure and manage.

Data Security

Encrypted storage for all credentials and configurations with secure transmission protocols.

Audit Logging

All administrative actions are logged for compliance and security monitoring.

Enterprise Ready

Built for organizations with strict compliance and governance requirements.

​
Need Help?

For additional support or questions about AI Model Governance & Configuration:

Custom User Roles

Manage organizational roles and permissions

Usage Data Export

Export and analyze usage data

Organizations & Workspaces

Understanding organizational structure