n8n-io/n8n · warning

AGENT_STATIC_PROMPT

AGENT_STATIC_PROMPT

Error message

Is input data required for '${node.name}'? If so, add an expression to the prompt. When following a chat trigger node, use { promptType: 'auto', text: '={{ $json.chatInput }}' }. Or use { promptType: 'define', text: '={{ ... }}' } to add dynamic data like input data.

What it means

Warning-level validator issue (code AGENT_STATIC_PROMPT) emitted by the agent validator when an Agent node's text prompt has no expression at all — i.e. it is empty or a plain literal with no '=' expression and no malformed '{{ }}' fragment. Such a static prompt cannot incorporate incoming item data, which defeats the purpose of an agent that should react to runtime input.

Source

Thrown at packages/@n8n/workflow-sdk/src/workflow-builder/plugins/validators/agent-validator.ts:52

		}

		const promptType = params.promptType as string | undefined;

		// Skip checks for auto/guardrails mode (undefined defaults to auto)
		if (!promptType || promptType === 'auto' || promptType === 'guardrails') {
			return issues;
		}

		// Check: Static prompt (no expression)
		const text = params.text;
		const hasValidExpression = containsExpression(text);
		const hasMalformedExpression = containsMalformedExpression(text);

		// Only warn about static prompt if there's NO expression at all
		// (MISSING_EXPRESSION_PREFIX will handle malformed expressions)
		if (!text || (!hasValidExpression && !hasMalformedExpression)) {
			issues.push({
				code: 'AGENT_STATIC_PROMPT',
				message: `Is input data required for '${node.name}'? If so, add an expression to the prompt. When following a chat trigger node, use { promptType: 'auto', text: '={{ $json.chatInput }}' }. Or use { promptType: 'define', text: '={{ ... }}' } to add dynamic data like input data.`,
				severity: 'warning',
				nodeName: node.name,
			});
		}

		// Check: No system message
		const options = params.options as Record<string, unknown> | undefined;
		const systemMessage = options?.systemMessage ?? params.systemMessage;
		if (
			!systemMessage ||
			(typeof systemMessage === 'string' && systemMessage.trim().length === 0)
		) {
			issues.push({
				code: 'AGENT_NO_SYSTEM_MESSAGE',
				message: `'${node.name}' has no system message. System-level instructions should be in the system message field.`,
				severity: 'warning',
				nodeName: node.name,

View on GitHub (pinned to 5ac6606e81)

Solutions

1. If following a chat trigger, set text to '={{ $json.chatInput }}' (promptType 'auto').
2. Otherwise set promptType 'define' and reference input data, e.g. '={{ $json.someField }}'.
3. Confirm the '=' prefix is present so n8n evaluates the value as an expression.

Example fix

// before
agent({ text: 'Summarize this' })
// after
agent({ promptType: 'auto', text: '={{ $json.chatInput }}' })

function hasExpression(value: unknown): boolean {
  return typeof value === 'string' && value.startsWith('=');
}
const text = agentParams.text;
if (!hasExpression(text)) {
  // warn: static prompt — add an expression
}

When it happens

Trigger: Defining an agent node with { text: 'Summarize this' } (no expression), or an empty text field, while expecting the agent to process incoming workflow data.

Common situations: First-draft agent config that hardcodes the prompt; copying a template that lost its expression; expecting chat input without wiring $json.chatInput.

Related errors

• AGENT_STATIC_PROMPT
• AGENT_NO_SYSTEM_MESSAGE
• The ‘text parameter is empty.
• The ‘text‘ parameter is empty.
• The ‘text‘ parameter is empty.

AI-assisted analysis of n8n-io/n8n@5ac6606e81 (2026-08-12). Data as JSON: /api/errors/2d8bc12c8de74e60. Report an issue: GitHub.