Introduction

Learn how to craft effective prompts for Lume AI to achieve accurate and efficient results in financial recasting, data transformation, and workflow automation. This guide covers key principles and practical examples to help you get the most out of AI-driven edits.

Key Principles

1. Be Specific & Clear

  • State exactly what you want to achieve
  • Include all necessary parameters
  • Avoid ambiguous or vague instructions

Good vs Bad Examples:

2. Contextual Awareness

Provide Sufficient Background

  • AI edits are more effective when given relevant context
  • Include details like industry jargon, audience type, or document purpose
  • A huge lever is providing an example

Example:

  • ❌ “Split the address”
  • ✅ “We are provided with a full address containing Street, City, State, and Zip. Please extract the street name. The addresses may vary in format, so please account for these differences.”

Leverage Data-Driven Insights

  • If applicable, reference specific data points or sources for accuracy

Example: “Here are a set of sample addresses: 123 Main St, New York, NY, 10002 and 456 Main St, APT 2014, New York, NY 10002.”

3. Iterative Refinement

Break Down Complex Edits

Large-scale edits should be iterative rather than single-pass.

Example:

  1. “Please extract the first name from the list of lenders.”
  2. “Append a unique id to the end of their name.”
  3. “If there are additional fields present related to name, please add them as well.”

Feedback & Adjustments

  • If an AI edit isn’t perfect, refine your prompt
  • Use structured feedback to improve results

Example: “The edit is now improved, but could you remove the unique_id.”

4. Structural & Formatting Enhancements

Use Formatting Directives

  • Specify whether edits should include bullet points, tables, or numbered lists

Example: “Restructure the name to be comma separated for easier readability. For example: ‘Jane, Smith‘“

Ensure Logical Flow

  • Indicate if content should be reordered for coherence

Example: “Rearrange these sections so the risk analysis follows the revenue projections.”

Best Practices

Do:

  • Start with a clear objective
  • Provide sample data when possible
  • Specify output format requirements
  • Break complex tasks into steps

Don’t:

  • Use vague instructions
  • Assume context is understood
  • Request multiple transformations in one prompt
  • Skip providing examples for complex tasks

Troubleshooting

If you’re not getting desired results:

  1. Add more specific examples
  2. Break down the request into smaller steps
  3. Clarify any assumptions
  4. Include edge cases you want to handle

Need Help?

Contact our support team via your dedicated account manager or email [email protected].