ToolJet/docs/versioned_docs/version-3.16.0-LTS/workflows/nodes/agent.md

id	title
agent	Agent Node

The Agent Node enables AI-powered automation within your workflows. It connects to AI Models and can use tools (Slack, Gmail, GitHub, etc.) to perform multi-step reasoning and task execution. The agent autonomously decides which tools to use and how to combine their results to accomplish complex tasks.

Configuration

Configuring Agent

Setting	Description
System Prompt	Instructions that define the agent's behavior, persona, and constraints.
User Prompt	The task or question for the agent to process. Supports dynamic values using {{ }} syntax.
Output Format	Defines the structure of the agent's final response. Use this to specify a JSON schema or format that the agent should follow when returning results.

AI Model

Connect the Agent node to an AI model datasource by linking it to the ai-model handle on the node.

Supported AI providers:

• OpenAI
• Anthropic
• Gemini
• Mistral AI

Model Parameters

Parameter	Description
Temperature	Controls randomness in responses. Higher values (0-1) produce more creative outputs.
Max Tokens	Maximum number of tokens the model can generate in a response.
Top P	Alternative to temperature for controlling randomness via nucleus sampling (0-1).
Max Steps	Maximum number of reasoning steps/iterations the agent can take.
Max Retries	Number of retry attempts for failed API calls.
Timeout	Maximum time in milliseconds for the agent to complete execution.
Stop Sequences	Sequences that signal the model to stop generating further text.

Tools

Tools allow the agent to interact with your data and perform actions. Each tool is a workflow node that the agent can invoke. The agent autonomously decides which tools to use based on the task and your system prompt instructions.

To add tools, drag nodes from the Agent node's tool handle to connect datasource queries, REST API calls, JavaScript nodes, or any other workflow nodes.

Supported Tool Types

You can use any workflow node as a tool, including:

• Datasource Queries: PostgreSQL, MySQL, MongoDB, and other database queries
• REST API: Connect to external services like Slack, GitHub, Gmail, Twilio, etc.
• JavaScript: Custom logic for data transformation or complex operations
• ToolJet Database: Query your ToolJet Database tables

Accessing Agent Node Data

Inside Tools

When the agent invokes a tool, it passes parameters that you can access within the tool node. Use the following syntax to retrieve these values:

aiParameters.<paramName>

The parameter names are determined by the agent based on your system prompt instructions. For example, if your system prompt instructs the agent to extract user_email from the user's message, you can access it in your tool as:

aiParameters.user_email

Outside Agent Node

Only the final result of the agent node can be accessed by other nodes in the workflow. If you need specific data in the output, define the expected output format in your system prompt.

To access the agent's output in subsequent nodes, use the following syntax:

<agentNodeName>.data

For example, if your agent node is named agent1:

agent1.data

Use Cases

Slack Notification Agent

Monitor events and send contextual notifications to the right Slack channels.

Tools:

Tool	Type	Description
getAlertDetails	PostgreSQL	Fetches alert information from the database
getUserOnCall	REST API	Gets the current on-call engineer
sendSlackMessage	Slack	Sends a message to a Slack channel
createIncident	REST API	Creates an incident in your incident management system

System Prompt:

You are an Alert Notification Agent.

When an alert is triggered:
1. Get alert details using "getAlertDetails"
2. Determine severity (critical, warning, info)
3. For critical alerts:
   - Get on-call engineer using "getUserOnCall"
   - Create incident using "createIncident"
   - Send urgent Slack message using "sendSlackMessage"
4. For warnings: send Slack message to #engineering-alerts
5. For info: send Slack message to #system-logs

Always include: alert name, severity, timestamp, and recommended action.

How It Works:

1. Trigger — A workflow trigger (e.g., a webhook from your monitoring system) fires and passes alert data like alert_id into the workflow.
2. User Prompt — The alert data is injected into the Agent Node's user prompt using dynamic syntax, for example: New alert triggered. Alert ID: {{ startNode.data.alert_id }}. This is the task the agent receives.
3. Agent Reasoning — The AI model reads the system prompt and user prompt, then plans its approach. It decides which tools to call and in what order.
4. Tool Execution — The agent starts executing:
   • Calls getAlertDetails with the alert ID to fetch severity, service name, and timestamp from PostgreSQL.
   • Based on the returned severity, it branches its logic. For a critical alert, it calls getUserOnCall to find the on-call engineer, then createIncident to open an incident, and finally sendSlackMessage to notify the #incidents channel with all the details.
5. Output — The agent compiles a final response summarizing the actions it took (e.g., incident ID created, Slack message sent, on-call engineer notified). This output is available to downstream nodes via agentNodeName.data.

Email Assistant Agent

Process incoming emails and draft responses or route them to the appropriate team.

Tools:

Tool	Type	Description
getEmailContent	Gmail	Fetches email subject, body, and sender info
classifyEmail	JavaScript	Analyzes email intent and urgency
draftReply	Gmail	Creates a draft response
forwardEmail	Gmail	Forwards to the appropriate department
logEmail	PostgreSQL	Logs the email for tracking

System Prompt:

You are an Email Processing Agent.

For each incoming email:
1. Get email content using "getEmailContent"
2. Classify the email type (inquiry, complaint, order, spam)
3. Based on classification:
   - Inquiries: draft a helpful reply using "draftReply"
   - Complaints: forward to support team using "forwardEmail"
   - Orders: log in database using "logEmail"
   - Spam: ignore
4. Log all processed emails in the database

Maintain a professional and helpful tone in all responses.

How It Works:

1. Trigger — A workflow trigger (e.g., a webhook from Gmail or a scheduled cron job) fires when a new email arrives and passes the email_id into the workflow.
2. User Prompt — The email ID is passed into the Agent Node's user prompt dynamically, for example: Process incoming email. Email ID: {{ startNode.data.email_id }}. This tells the agent which email to work on.
3. Agent Reasoning — The AI model reads the system prompt and user prompt, then determines the sequence of tool calls needed to process this email.
4. Tool Execution — The agent starts executing:
   • Calls getEmailContent with the email ID to fetch the subject, body, and sender details from Gmail.
   • Passes the email content to classifyEmail, a JavaScript node that returns the classification (e.g., "complaint").
   • Based on the classification, the agent branches: for a complaint, it calls forwardEmail to route it to the support team. For an inquiry, it would call draftReply to compose a response.
   • Finally, it calls logEmail to record the email and the action taken in PostgreSQL.
5. Output — The agent returns a summary of what it did (e.g., email classified as "complaint", forwarded to support@company.com, logged with tracking ID #4521). This output is available to downstream nodes via agentNodeName.data.

Limitations

• The agent's performance depends on the underlying AI model's capabilities
• Complex multi-tool workflows may require higher max steps settings
• API rate limits from AI providers may affect execution

---

Need Help?

• Reach out via our Slack Community
• Or email us at support@tooljet.com
• Found a bug? Please report it via GitHub Issues