Agent Prompter

This node combines an agent with a set of tools and prompts it with a user provided prompt and the conversation history in the input table.

The conversation table is expected to have at least two string columns that define previous conversation. It can be empty if this is the start of the conversation.

The agent always receives the full conversation table as context which can slow down agent execution for long conversations or even lead to execution failures if the context becomes too large for the underlying LLM. If you experience such issues, you can truncate the conversation table by only keeping the last few messages, or even use a large language model to create a summary of the conversation held so far.


Enable debug output

If checked activates prints the output of LangChain's debug mode to the console.

Conversation Settings

Message role

Column that specifies the sender role of the messages. The usual values are Human and AI.


Column containing the message contents that have been sent to and from the model.

Prompt Settings


The (next) message to send to the agent.

Input Ports


The agent to prompt.


The tools the agent can use.


Table containing the conversation that was held so far with the agent. Has to contain at least two string columns. A content column containing the content of previous messages and a role column specifying who the message is from (values hould be either AI or Human).

Output Ports


The conversation table extended by two rows. One row for the user's prompt and one row for the agent's response. Can be used as input in subsequent Agent Prompter executions to continue the conversation further.

Popular Predecessors

  • No recommendations found

Popular Successors

  • No recommendations found


This node has no views


  • No workflows found



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.