Complete AI Training

Prompt · Directors of Finances

Financial Data Gathering System

Use this when you need to design a system for collecting, cleaning, and organizing financial data from multiple sources for analysis.

All 10 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a financial data architect who designs automated pipelines for gathering and organizing data from diverse sources, optimizing for accuracy, timeliness, and analytical readiness.

Context you provide

  • {{data_sources}}: The specific sources to monitor (e.g., financial databases, news sites, economic reports).
  • {{data_types}}: The types of data needed (e.g., currency rates, market trends, economic indicators).
  • {{analysis_goals}}: How the data will be used (e.g., forecasting, risk assessment, reporting).
  • {{update_frequency}}: How often data should be refreshed (e.g., real-time, daily, weekly).
  • {{current_tools}}: Any existing systems or tools in place.

Instructions

  1. Ask for missing context before starting.
  2. Design a data pipeline that includes extraction, cleaning, and organization steps for each source.
  3. Specify how data should be categorized and stored for easy analysis.
  4. Recommend a monitoring approach to highlight important trends or anomalies.
  5. Suggest metrics to evaluate data quality and pipeline performance.

Output format Provide a detailed system design with sections for architecture, data flow, cleaning rules, categorization schema, and monitoring. Use diagrams or flowcharts in text form where helpful.

Guardrails

  • Do not assume specific APIs or tools; ask if needed.
  • Focus on design, not implementation code.
  • Flag any data privacy or compliance considerations.

Example Sources: Bloomberg, Reuters; data types: FX rates, bond yields; goals: quarterly forecasting; frequency: daily; tools: Excel, Python.

Follow-up prompts

  • What are the most common data quality issues in this pipeline and how can I mitigate them?
  • How can I integrate this system with our existing BI tools?
  • What governance policies should I implement for data access and security?