Field Modes

Field Modes

Overview

Every node in your workflow has fields that need to be configured—recipient emails, message content, API parameters, or data to process. Langdock gives you three intelligent ways to fill these fields, each optimized for different scenarios.

Choose the right mode for each field to balance flexibility, control, and AI credit usage.

The Three Field Modes

These modes apply to most node fields. Some nodes like Condition have their own modes (Manual and Prompt AI) optimized for their specific purpose.

Auto Mode

Let the workflow automatically determine the best value based on context from previous nodes.

How it works:

• Analyzes all data from previous nodes in the workflow

• Intelligently matches field requirements with available data

• Automatically fills the field with the most appropriate value

Best for:

• Straightforward data mapping (form data → spreadsheet)

• Fields where the context is obvious

• When you want flexibility and don’t need exact control

• Reducing configuration time

Example:

Scenario: Sending email based on form submission
Field: "Recipient Email"
Mode: Auto
Result: Automatically uses email from form trigger

Advantages:

• ✅ Fast setup—minimal configuration needed

• ✅ Very flexible—adapts to varying data structures

• ✅ Great for covering edge cases automatically

• ✅ Handles unexpected data gracefully

Disadvantages:

• ❌ Consumes AI credits (uses AI to determine values)

• ❌ Less control over exact output

• ❌ Can get expensive with frequent executions

---

Manual Mode

Enter exact values or reference specific data from previous nodes with complete control.

Manual Mode

How it works:

• What you type is exactly what appears (no AI processing)

• Use variables to insert data from previous nodes: {{trigger.name}}

• Combine static text with dynamic variables

Best for:

• Fixed values (API keys, webhook URLs, signatures)

• Exact data references you want to control

• Combining static text with variables

• When you need predictable, consistent output

Example:

Field: "Email Subject"
Mode: Manual
Value: "New order #{{trigger.output.order_id}} from {{trigger.output.customer_name}}"
Result: "New order #12345 from Alice Smith"

Advantages:

• ✅ Complete control over output

• ✅ No AI credits used

• ✅ Predictable and consistent

• ✅ Fastest execution (no AI processing)

• ✅ Perfect for templates and fixed formats

Disadvantages:

• ❌ Requires manual configuration

• ❌ Can’t generate dynamic content based on context

• ❌ You must know exact variable paths

---

AI Prompt Mode

Give natural language instructions for the AI to generate dynamic content based on workflow data.

AI Prompt Mode

How it works:

• Write instructions describing what content should be generated

• AI analyzes data from previous nodes and creates appropriate content

• Can reference specific data using variables: {{trigger.output..message}}

• Generates unique output each time based on context

Best for:

• Email composition (subject lines, body content)

• Content generation (summaries, descriptions)

• Dynamic messages that adapt to context

• Transforming or reformatting data creatively

Example:

Field: "Email Body"
Mode: AI Prompt
Instructions: "Write a friendly 2-paragraph response to {{trigger.message}}, addressing their concern about {{agent.issue_category}} and offering a solution."
Result: Personalized email generated based on actual message content

Advantages:

• ✅ Creates intelligent, context-aware content

• ✅ Adapts to different situations automatically

• ✅ Saves time writing templates

• ✅ Can combine multiple data sources creatively

• ✅ Produces natural, varied output

Disadvantages:

• ❌ Consumes AI credits

• ❌ Slightly slower than manual mode

• ❌ Output may vary between executions

• ❌ Requires clear prompting for best results

Choosing the Right Mode

Use this decision flow to select the appropriate mode:

1

Is the value always the same?

Use Manual mode with static text.

2

Is the value from a previous node, unchanged?

Use Manual mode with variables.

3

Do you need AI to generate or transform content?

If yes → AI Prompt Mode. If no → Auto Mode.

Mode Comparison

Feature	Auto	Manual	AI Prompt
Configuration Time	Fast	Medium	Medium
AI Credits	Yes	None	Yes
Control	Low	High	Medium
Flexibility	High	Low	High
Best For	Simple mapping	Fixed values	Content generation

Real-World Examples

Customer Support Workflow

Trigger: Form submission (customer complaint)

Action: Send email response
- To: Auto (uses form.email automatically)
- From: Manual → "[email protected]"
- Subject: AI Prompt → "Write a professional subject line about {{form.output.issue_type}}"
- Body: AI Prompt → "Draft a helpful response to: {{form.output.message}}"

Data Processing Workflow

Trigger: New spreadsheet row

Action: Create CRM record
- Name: Manual → "{{trigger.output.customer_name}}"
- Email: Auto (matches automatically)
- Notes: AI Prompt → "Summarize: {{trigger.output.feedback}}"
- Status: Manual → "New Lead"

Notification Workflow

Agent: Analyze document

Action: Send notification
- Message: AI Prompt → "Create an executive summary of {{agent.output.analysis}}"
- Recipient: Manual → "[email protected]"

Using Variables in Manual and AI Prompt Modes

Both Manual and AI Prompt modes support variables from previous nodes.

Syntax:

{{node_name.output.field_name}}
{{node_name.output.nested.field}}
{{node_name.output.array[0].property}}

Examples:

{{trigger.output.email}}            ← Form field
{{agent.output.summary}}           ← Agent output
{{http_request.output.data.userId}} ← API response
{{loop_item.output.name}}          ← Current loop item

Tip: Type {{ in any Manual or AI Prompt field to see available variables from previous nodes.

Best Practices

• Start with Auto, refine as needed: Begin with Auto mode for most fields. If it doesn’t work as expected, switch to Manual or AI Prompt for more control.

• Use Manual for fixed values: API keys, email addresses, signatures, and webhook URLs should always use Manual mode.

• Be specific in AI prompts: Instead of “write an email”, use “write a professional 2-paragraph email thanking for their interest in <...>”.

• Minimize AI mode usage: Both Auto and AI Prompt modes consume AI credits. Use Manual mode for fixed values and simple variable references to reduce costs.

• Test with real data: Run test workflows with actual data to verify each mode behaves as expected before publishing.

Next Steps

• Core Concepts — Learn how nodes work together in workflows

• Condition Node — Learn about Manual and Prompt AI modes for conditions

• Agent Node — Use AI for content analysis and generation

• Getting Started — Build your first workflow