LLM Node

The LLM node lets you ask AI to help with text. It’s like having a smart assistant that can summarize long emails, categorize support tickets, write responses, extract information from documents, and much more.

LLM node configuration form — LLM configuration — pick a model, then write the system and user instructions.

When to Use

Summarizing - Turn a long document into bullet points
Categorizing - Sort emails into “Sales”, “Support”, “Spam”, etc.
Extracting - Pull out names, dates, and numbers from messy text
Writing - Generate email replies, reports, or social posts
Translating - Convert text to another language
Analyzing - Detect if a message is positive or negative, urgent or not
Reformatting - Turn a paragraph into a list, or vice versa

Use AI when you need to understand meaning. For simple tasks like removing spaces or splitting text, use Execute Code instead - it’s faster and costs less.

Example: Email Categorizer

Automatically categorize incoming support emails:

Set up the event trigger

Add an App Trigger node for Gmail to receive incoming emails.

Configure LLM

Add an LLM node with:System prompt:

You are an email classifier for a software company's support team.
Categorize emails into exactly one of these categories:
- BUG_REPORT
- FEATURE_REQUEST
- BILLING
- ACCOUNT_ACCESS
- GENERAL_INQUIRY

Respond with only the category name, nothing else.

User message:

Categorize this email:

From: {{event_from_app_1.email.from}}
Subject: {{event_from_app_1.email.subject}}
Body: {{event_from_app_1.email.body}}

Route based on category

Add a Multi-Condition node using {{llm_1.response}} to route to different handling workflows.

Example: Meeting Summary Generator

Create structured meeting notes from transcripts: System prompt:

You are an expert at summarizing business meetings. Create clear,
actionable meeting summaries.

User message:

Summarize this meeting transcript into:
1. Key decisions made
2. Action items with owners
3. Open questions
4. Next steps

Transcript:
{{parse_file_1.content}}

Output usage:

# Send to Slack
{{llm_1.response}}

# Store for records
{{set_variable_1.value}}

Example: Data Extraction

Extract structured data from unstructured text: System prompt:

You are a data extraction assistant. Extract information precisely
as requested and return it in valid JSON format.

User message:

Extract the following from this invoice:
- Vendor name
- Invoice number
- Date
- Line items (description, quantity, unit price)
- Total amount

Return as JSON.

Invoice text:
{{parse_file_1.content}}

Using the extracted data: Define the invoice fields in the node’s Structured Output schema, and downstream nodes can reference them directly — no JSON parsing needed:

{{llm_1.structuredOutput.vendor_name}}
{{llm_1.structuredOutput.total_amount}}

Tips for Getting Good Results

Be Specific About What You Want

Good: "Summarize in 3 bullet points, max 15 words each"
Bad: "Summarize this"

The more specific you are, the better the result.

Give Background Information

Good: "You're reading customer feedback for our project management software"
Bad: "Analyze this feedback"

Context helps the AI understand what it’s working with.

Tell It Exactly How to Respond

Good: "Respond with only 'APPROVE' or 'REJECT', nothing else"
Bad: "Tell me if this should be approved"

If you need a specific format, say so clearly.

Show Examples

Good:
"Categorize as positive, negative, or neutral.

Examples:
- 'Love this product!' → positive
- 'Terrible experience' → negative
- 'It works fine' → neutral

Now categorize: {{input}}"

Examples help the AI understand exactly what you’re looking for.

Structured Output

When downstream steps need to parse the answer, don’t ask for JSON in the prompt — use the node’s Structured Output setting. Define the fields you want (for example sentiment, topics, urgency, summary) in the schema builder, and the node returns them as a real object on the structuredOutput output:

{{llm_1.structuredOutput.sentiment}}
{{llm_1.structuredOutput.urgency}}

This is much more reliable than parsing JSON out of free text, and Condition or Resolve Value nodes can use the fields directly.

Use temperature 0 when you need consistent, structured output. Higher temperatures can cause format variations.

Which Model Should I Choose?

What You’re Doing	Best Choice
Complex analysis, hard questions	Largest available model (most capable, higher cost)
Most everyday tasks	Mid-tier model (good balance of speed and capability)
Simple tasks, lots of them	Smallest/fastest model (lowest cost)
Very long documents	Models with larger context windows

Model names and capabilities change frequently. The model selector in the UI shows current options with their capabilities.

Each Call Starts Fresh

Every LLM node call is independent — it has no memory of earlier LLM calls in the workflow. If a later step needs something from an earlier answer, pass it explicitly:

Earlier answer: {{llm_1.response}}

Now answer this follow-up question: ...

Advanced: the messagesOverwrite setting lets you supply the full message history yourself (an array of { role, content } messages built by an earlier node), replacing the system/user instructions entirely.

Letting the AI Use Your Apps

The LLM node isn’t limited to text. In the config panel you can enable Built-in Skills — Web Search and Web Extract (both on by default) and Execute Python Code — and bind Integrations: connected apps like Gmail, Jira, or Slack whose actions the model can call as tools while the step runs. That turns a single LLM step into a mini agent: it can look up an email thread, create a ticket, and then write its answer — all in one node.

LLM Integrations

Bind connected apps to the node, choose which actions the model may call, and guide it with per-action usage notes.

Saving Money on AI Costs

Use simpler models for simple tasks - Don’t use GPT-4 when GPT-3.5 would work fine
Keep responses short when possible - If you only need a yes/no answer, don’t allow long responses
Save results to reuse later - Use Update Variable so you don’t have to ask the same question twice
Skip AI when you don’t need it - Use Condition nodes to avoid unnecessary AI calls

Tips

Use the “Fill by AI” feature when configuring prompts. It can help you write better prompts based on your workflow context.

Chain multiple LLM nodes for complex tasks: one to analyze, one to decide, one to generate. This improves reliability and makes debugging easier.

Settings

string

default:"LLM"

What to call this node (shown on the canvas).

string

default:"llm_1"

A short code to reference this node’s response.

string

required

Which AI provider to use — OpenAI, Anthropic, Google, and others. Pick it with the visual model selector.

string

required

Which specific AI model to use. Newer/larger models are smarter but cost more. The selector shows each model’s capabilities (images, audio, files, and more).

string

required

System instructions — background context that tells the AI how to behave.

string

required

User instructions — what you want the AI to do. You can include data from previous nodes using {{node_name.value}}.

array

Files to send along with the instructions — images, audio, PDFs, and more. See Working with files and AI.

number

default:"0.7"

How creative vs. consistent the AI should be. 0 = same answer every time. 1 = more varied and creative. Part of the collapsible Model Configuration section.

number

default:"1000"

How long the response can be. A token is roughly 3-4 characters for English text (varies by language and content).

number

default:"3"

How many times to try again if something goes wrong.

object

A schema describing the fields you want back. When set, the node returns a parsed object on the structuredOutput output.

object

Toggles for the built-in skills: Web Search and Web Extract (on by default) and Execute Python Code (off by default).

array

Connected apps and the actions the model may call. Configure them in the Integrations section — see LLM Integrations.

Outputs

string

The model’s text response.

object

The parsed object matching your Structured Output schema (only when the schema is configured).

string

The model’s reasoning content, when the selected model exposes it.

string

Why the model stopped generating:

stop - Natural completion
length - Hit max tokens limit

object

Results of every skill and integration action the model called, grouped by tool name.

array

Files the model generated (images, audio, charts) or that its tools produced — usable by later nodes.

array

Integrations that could not be offered to the model — for example, because their connection was removed or disabled.

string

The model that actually served the call.

string

The resolved user instructions that were sent to the model.

boolean

Whether the call completed. On failure, error holds the details.

LLM Integrations

Let the model call actions on your connected apps.

Execute Workflow

Run another workflow you’ve built and use its output.

Execute Code

Process AI responses with custom code.

Overview

Triggers

Actions

Logic

Communication

When to Use

Example: Email Categorizer

Example: Meeting Summary Generator

Example: Data Extraction

Tips for Getting Good Results

Be Specific About What You Want

Give Background Information

Tell It Exactly How to Respond

Show Examples

Structured Output

Which Model Should I Choose?

Each Call Starts Fresh

Letting the AI Use Your Apps

LLM Integrations

Saving Money on AI Costs

Tips

Settings

Outputs

LLM Integrations

Execute Workflow

Execute Code

​When to Use

​Example: Email Categorizer

​Example: Meeting Summary Generator

​Example: Data Extraction

​Tips for Getting Good Results

​Be Specific About What You Want

​Give Background Information

​Tell It Exactly How to Respond

​Show Examples

​Structured Output

​Which Model Should I Choose?

​Each Call Starts Fresh

​Letting the AI Use Your Apps

LLM Integrations

​Saving Money on AI Costs

​Tips

​Settings

​Outputs

​Related Nodes

LLM Integrations

Execute Workflow

Execute Code

When to Use

Example: Email Categorizer

Example: Meeting Summary Generator

Example: Data Extraction

Tips for Getting Good Results

Be Specific About What You Want

Give Background Information

Tell It Exactly How to Respond

Show Examples

Structured Output

Which Model Should I Choose?

Each Call Starts Fresh

Letting the AI Use Your Apps

Saving Money on AI Costs

Tips

Settings

Outputs

Related Nodes