Skip to main content
Use ai.action when you only need a prompt and an output. It runs one model call and does not let the model call tools.

​
Capabilities

  • Pass task instructions in instructions and task data in user_prompt.
  • Use output_type when you need a string, list, or JSON-shaped response for downstream actions.
  • Tune provider-specific behavior with model_settings.

​
Structured outputs

Use output_type when a downstream action needs a predictable shape.
  • Use a scalar such as str or int for simple classification or routing.
  • Use a JSON schema object when you need named fields.
  • Tracecat parses valid JSON before storing it in the action result.

​
Reference

​
ai.action

Call an LLM with a given prompt and model (no tools).

​
Inputs

​
model_name
string
required
Name of the model to use.
​
model_provider
string
required
Provider of the model to use.
​
user_prompt
string
required
User prompt to the agent.
​
base_url
string | null
Base URL of the model to use.Default: null.
​
instructions
string | null
Instructions for the agent.Default: null.
​
max_requests
integer
Maximum number of requests for the agent.Default: 45.
​
model_settings
object | null
Model settings for the agent.Default: null.
​
output_type
string | object | null
Output type for agent responses. Select from a list of supported types or provide a JSONSchema.Default: null.
​
retries
integer
Number of retries for the agent.Default: 3.

​
Examples

Extract structured fields from an alert 
- ref: extract_alert
  action: ai.action
  args:
    model_name: gpt-4.1-mini
    model_provider: openai
    instructions: |
      Extract the alert into the requested schema.
      Use null for fields that are missing.
    user_prompt: |
      Parse this alert and normalize the key fields:

      ${{ TRIGGER.raw_alert }}
    output_type:
      type: object
      properties:
        severity:
          type: string
        user:
          type:
            - string
            - "null"
        src_ip:
          type:
            - string
            - "null"
        needs_escalation:
          type: boolean
      required:
        - severity
        - needs_escalation
Classify an email triage decision 
- ref: classify_email
  action: ai.action
  args:
    model_name: claude-3-5-sonnet-latest
    model_provider: anthropic
    instructions: |
      Return one of: phishing, benign, spam, unknown.
    user_prompt: |
      Subject: ${{ TRIGGER.subject }}
      Sender: ${{ TRIGGER.sender }}
      Body:
      ${{ TRIGGER.body }}
    output_type:
      type: string
      enum:
        - phishing
        - benign
        - spam
        - unknown