Claude Block

The Claude Block allows you to interact with Anthropic's powerful language models (like Claude 3 Opus, Sonnet, and Haiku). It supports multi-turn conversations through built-in history management and provides fine-grained control via advanced settings.

Configuration

Field	Required	Description
API Key	✅	Your Anthropic API key (usually mapped from the Secret Vault).
Model	✅	The specific Anthropic model to use (e.g., `claude-3-opus-20240229`).
User Prompt	✅	The main text or question to send to the model.
System Prompt	—	Instructions that define the assistant's persona or operational constraints.
Enable History	—	Toggle to maintain conversational context across API calls.

History Settings

If Enable History is turned on, the following fields are required:

Storage Object Variable (Required): A variable mapped to a Storage Object to persist the chat history.
Chat ID: A unique identifier for the conversation session.
Message Count: The number of previous messages to retain for context.

Advanced Settings

Toggle Advanced Settings to customize generation parameters:

Temperature (0 to 1): Controls the randomness of the output.
Max Output Tokens: Limits the length of the response.
Top P: Nucleus sampling value.

Output Variable

Specify a Variable Name to store the result.

Success Payload

{
  "success": true,
{
  "error_key": "rate_limit_error",
}

Error Handling

API_KEY_MISSING / SECRET_ERROR — Missing or invalid API key.
MODEL_MISSING — No model was specified.
PROMPT_MISSING — The user prompt was empty.
HISTORY_VAR_MISSING — History was enabled but no storage object was provided.
RUNTIME_ERROR — An unexpected issue occurred during the API call.
rate_limit_error / overloaded_error — Standard Anthropic API errors.

Claude