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

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}}

# Send to Slack
{{llm_1.response}}

# Store for records
{{set_variable_1.value}}

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

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}}

// In an Execute Code node, parse the JSON
const invoice = JSON.parse(input.llm_1.response);
return {
  vendorName: invoice.vendor_name,
  total: invoice.total_amount
};

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

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

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

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

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

Now categorize: {{input}}"

Always respond in valid JSON format. Do not include any text
outside the JSON object.

Analyze this customer review and respond with:
{
  "sentiment": "positive" | "negative" | "neutral",
  "topics": ["array", "of", "topics"],
  "urgency": 1-5,
  "summary": "one sentence summary"
}

Review: {{input}}

LLM 1: "What's the capital of France?"
AI: "Paris"

LLM 2: "What's its population?" (with memory enabled)
AI: "Paris has about 2.1 million people..."