Agent Prompter

This node builds and executes an agent that responds to a single user prompt using a language model and a set of user-defined tools.

Each tool is represented as a KNIME workflow with configurations (e.g., strings, numbers, column selection) and can optionally accept input data tables. While the agent does not have access to raw data, it is informed about available tables through metadata — including column names and types — enabling it to select suitable data for each tool as needed.

When the node is executed, the agent reasons step-by-step to fulfill the user’s prompt. It may call one or more tools in sequence, using the output of one tool as input for another. The model autonomously selects tools and input data based on the prompt and the tools’ names and descriptions. Including clear tool descriptions and example use cases significantly improves the agent’s decision-making.

The entire internal reasoning process — including tool calls and decisions — is captured and available via the conversation output table. This node is designed for non-interactive, one-shot execution. For interactive, multi-turn conversations, use the Chat Agent Prompter node.

Options

System message

Instructions provided by the workflow builder that guide the agent's behavior. It typically defines the agent’s role, its tone, boundaries, and behavioral rules.This message is prioritized over the user message and should not contain any information that the user can inject in order to prevent prompt injection attacks.

User message

Message from the end user, prioritized behind the developer message.

Tool column

The column of the tools table holding the tools the agent can use.

Conversation column

The column containing the conversation history if a conversation history table is connected.

Conversation column name

Name of the conversation column if no conversation history table is connected.

Iteration limit

Limits the maximum number of steps the agent can take to avoid getting stuck in an endless loop.

When iteration limit is reached

Specify the behavior of the agent when the iteration limit is reached.

Available options:

Fail: Execution fails if the iteration limit is reached.
Final response: A user message is appended to the conversation that prompts the LLM to generate a final response based on all previously generated messages.

Iteration limit prompt

This message guides the chat model when generating the final response based on all previously generated messages. It can be used to specify how the LLM should behave if information is missing because the agent stopped before executing tools.

Debug mode

In debug mode, tool executions are displayed as meta nodes in the agent workflow and the meta node is kept in case of an error in the tool.

Data message prefix

Prefix for the data message shown to the agent. You can use this to customize the instructions about the data repository.

Error Handling Settings

Error handling

Specify the behavior of the agent when an error occurs.

Available options:

Fail: Execution fails if there is an error.
Error column: Execution is stopped if there is an error. The output table will contain an additional string column containing error messages. If there was an error, the corresponding row will contain a missing value in the conversation column.

Continue existing error column

If selected, the output table will continue the error column selected from the input conversation table.

Error column name

Name of the newly generated error column.

Error column

The column containing the errors if a conversation history table is connected.

Input Ports

: The chat model to use.
: The tools the agent can use.
…: The table containing the conversation held so far.
…: The data inputs for the agent.

Output Ports

: The conversation between the LLM and the tools reflecting the agent execution.
…: The data outputs of the agent.

Popular Predecessors

No recommendations found

Popular Successors

No recommendations found

Views

This node has no views

Workflows

No workflows found

Developers

You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.

Installation

To use this node in KNIME, install the extension KNIME Python Extension Development (Labs) from the below update site following our NodePit Product and Node Installation Guide:

v5.10

A zipped version of the software site can be downloaded here.

Plugin provider: KNIME AG, Zurich, Switzerland

Plugin version: 5.10.0.v202601271422

On NodePit since: 2026-02-18

Last update: 2026-02-24

Tags: Modern UI

KNIME versions: Since v5.5

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!