Model Settings
The Model Settings define how AI models are used during agent execution in Flowable. These settings are essential for specifying the AI vendor, model, temperature, and authentication method.
Model Settings become available when Advanced Configuration is enabled for an agent model.
For guidance on configuring models centrally across environments, see the setup guide.
Enabling Advanced Configuration
To configure model settings, first enable Advanced Configuration in the Capabilities tab of the agent:
Once enabled, additional options for model configuration will appear:
Supported AI Vendors
Flowable currently supports the following AI vendors:
- OpenAI
- Anthropic
- Azure OpenAI (a custom endpoint URL can be provided)
Each vendor supports different models and may require specific configuration details.
Configurable Options
When defining a model configuration, you can set:
- Vendor – Choose from OpenAI, Anthropic, or Azure OpenAI
- Model – Define the specific model to use (e.g.,
gpt-4
,claude-3-opus
, etc.) - Temperature – Controls the randomness or determinism of responses
- Authentication – Configure how tokens are securely provided
Token Configuration
You can provide an access token in one of the following ways:
- Inline – Entered directly in the configuration (not recommended for production)
- Secure reference – Linked through a secret or OAuth token managed in Flowable Control or Flowable Hub
Flowable Control
To manage secrets in Flowable Control, go to Platform > Secrets, click the arrow next to Select an action, and choose Create:
This ensures secure and centralized management of credentials for on-premise or self-managed installations.
Flowable Hub (Cloud only)
For cloud customers, secrets can be securely managed via Flowable Hub. Go to Environment > Secrets and click Add secret:
This provides the same secure handling of secrets across cloud-managed environments.
Summary
- Model Settings define which AI vendor and model an agent uses
- Advanced Configuration must be enabled to access these options
- Supports OpenAI, Anthropic, and Azure OpenAI
- Authentication can be linked securely via Flowable Control (on-prem) or Flowable Hub (cloud)
- Model name and temperature are fully configurable
- See AI Model Setup Guide for centralized configuration setup