DocumentationWorkflowsAI and agents

AI Agent node

Calls a model and answers the user prompt. Optionally with tools (Microsoft Graph, HTTP, calculator, …) that the agent picks on its own. Learn how to configure it, map inputs and outputs, run a test and resolve common errors.

8 min readUpdated

What this node does

Calls a model and answers the user prompt. Optionally with tools (Microsoft Graph, HTTP, calculator, …) that the agent picks on its own.

Use AI Agent as a clearly defined step in an anymize workflow.

  • Processes one input.
  • Provides one output for following steps.
  • Can call approved tool nodes autonomously.

Set up the node

  1. 01Open a workflow and add AI Agent from the node catalog.
  2. 02Complete the required fields and map values from previous steps.
  3. 03Run the node with a small test record and inspect its output.
  4. 04Connect the successful output and activate the workflow after an end-to-end test.

Operations and modes

AI Agent has one focused purpose. Its available settings appear when you select the node.

Settings

FieldMeaningArea
ModelAnymize Waterfall is the EU-hosted default (privacy-first). Claude models for trickier tasks.Standard
User prompt (required)Configure this value in the node panel.Standard
Output formatChoices: Text (default), JSON (structured)Standard
JSON structure (optional)Configure this value in the node panel.Standard
ToolsTools the agent can call. The LLM decides on its own when each one fits.Standard
System messagePrepended to the model. Steers personality + rules.Standard
Maximum reasoning stepsMaximum model rounds (1 to 25). Each round can call several tools. The run fails if the agent does not produce a final answer.Standard
Credit budgetStops further model and tool calls at this usage (1 to 100000 credits). A model call already in progress can exceed the budget.Standard
Maximum tool callsLimits each agent step to 1 to 100 tool calls, including multiple calls requested in a single model round.Standard

Inputs and outputs

InputMeaningType
user promptThe user message to the agent. Overrides the inline prompt field.text
system promptSystem message / role. Overrides the inline system message.text
OutputMeaningType
outputThe agent's answer (final assistant message).text
stepsConfigure this value in the node panel.json

Example and test run

Research agent with calculator + HTTP tool: begin with a small, recognizable record. Inspect the output and only map fields that are present there.

Test-run example

{
  "userPrompt": "Wie viele Einwohner hat Berlin laut Wikipedia, und wie viel ist das mal 0.2?",
  "systemPrompt": "Du bist ein präziser Recherche-Assistent. Antworte kurz auf Deutsch."
}

Access and security

Before activation, review which data enters this step and what its output contains.

Store keys and credentials in the protected connection manager. Never paste them into normal workflow fields, test data or descriptions.

Troubleshooting

  • No output: inspect the latest run and confirm that the previous node returned the expected fields.
  • Empty variable: open the previous step output and use a field name from the real test data.