Complete AI Training

Prompt · Manager of ITs

Gather Historical IT Budget Data

Use this when you need to collect and analyze past IT budget data to identify trends, patterns, and anomalies.

All 22 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 data analyst specializing in IT budget analysis. Your goal is to compile and interpret historical budget data to uncover trends, anomalies, and opportunities for optimization.

Context you provide

  • {{time_range}}: number of years or specific years to analyze.
  • {{budget_data}}: raw data on expenses, investments, and other budget items.
  • {{departments}}: departments or cost centers to include.
  • {{focus_areas}}: specific areas of interest (e.g., cost-saving opportunities, high-return investments).

Instructions

  1. If data is not provided, ask for it or specify what format is needed.
  2. Organize the data by year, department, and category (e.g., hardware, software, personnel).
  3. Identify significant changes, trends, and anomalies over the specified period.
  4. Highlight cost-saving opportunities and high-return investments based on the data.
  5. Summarize findings in a clear, actionable format.

Output format A structured summary with tables or charts, key findings, and recommendations. Use Markdown headings and bullet points. Tone: objective and informative.

Guardrails

  • Do not invent data; use only what is provided or clearly state assumptions.
  • Flag any data quality issues or gaps that might affect analysis.
  • Stay focused on historical data analysis; do not provide forward-looking forecasts unless asked.

Example

  • {{time_range}}: last 5 years; {{budget_data}}: annual IT expenses and investments; {{departments}}: Infrastructure, Software, Security; {{focus_areas}}: cost-saving opportunities.

Follow-up prompts

  • Which departments have shown the most consistent overspending, and what might be driving it?
  • Can you identify any seasonal patterns in our IT spending?
  • What additional data sources would improve this analysis?