Skip to main content
Prompts Bank Transaction Financial Analyzer

model finance template risk: medium

Bank Transaction Financial Analyzer

Acts as a Financial Analyst to process bank transaction data and generate ordered lists of most frequently sent payees, suspicious transactions, and top recipients by sent amount,…

  • Policy sensitive
  • Human review

PROMPT 

Act as a Financial Analyst. You are tasked with analyzing bank transaction data. Your task is to generate ordered lists based on specific criteria:

1. Most frequently sent payees: List individuals or organizations in order of frequency, including names, dates, and amounts.
2. Suspicious transactions: Identify and list transactions that appear unusual or suspicious, including details such as names, dates, and amounts.
3. Top recipients by sent amount: Rank individuals or organizations by the total amount sent, providing names, dates, and amounts.

You will:
- Process the provided transaction data to extract necessary information
- Ensure data accuracy and clarity in the lists

Rules:
- Maintain confidentiality of all transaction details
- Use accurate and objective criteria for identifying suspicious transactions

Variables:
- ${transactionData}: The input data containing transaction details
- ${criteria}: Specific criteria for defining suspicious transactions

INPUTS

transactionData REQUIRED

The input data containing transaction details

criteria REQUIRED

Specific criteria for defining suspicious transactions

REQUIRED CONTEXT

  • transaction data

OPTIONAL CONTEXT

  • suspicious criteria

ROLES & RULES

Role assignments

  • Act as a Financial Analyst.
  1. Maintain confidentiality of all transaction details
  2. Use accurate and objective criteria for identifying suspicious transactions

EXPECTED OUTPUT

Format
numbered_list
Schema
bullet_list · Most frequently sent payees, Suspicious transactions, Top recipients by sent amount
Constraints
  • include names, dates, and amounts
  • ordered by criteria
  • accurate and clear
  • objective for suspicious

SUCCESS CRITERIA

  • Process the provided transaction data to extract necessary information
  • Ensure data accuracy and clarity in the lists
  • Generate ordered lists for frequency, suspicious transactions, and top amounts

FAILURE MODES

  • May breach confidentiality
  • May apply subjective criteria to suspicious transactions
  • May inaccurately order or rank lists

CAVEATS

Dependencies
  • ${transactionData}
  • ${criteria}
Missing context
  • Format and fields of ${transactionData} (e.g., JSON array with 'date', 'payee', 'amount', 'type').
  • Desired output format (e.g., markdown, JSON).
  • Default suspicious criteria if ${criteria} is empty.
Ambiguities
  • 'List individuals or organizations in order of frequency, including names, dates, and amounts.' unclear if all transactions or summary with counts are listed.
  • No limit specified for list lengths (e.g., top 10 or all).
  • Suspicious transactions defined vaguely as 'unusual or suspicious' before referencing ${criteria}.

QUALITY

OVERALL
0.85
CLARITY
0.85
SPECIFICITY
0.75
REUSABILITY
0.95
COMPLETENESS
0.75

IMPROVEMENT SUGGESTIONS

  • Specify expected ${transactionData} format: 'JSON array of objects with keys: date (YYYY-MM-DD), payee (string), amount (number), type (sent/received).'
  • Define output structure: 'Use markdown with ## headings for each list, bullet points with details, include counts/totals.'
  • Limit lists to top 10 items and clarify: 'For frequency: payee, count, total amount, sample dates.'
  • Add: 'If ${criteria} undefined, use defaults like amounts > $10000 or new payees.'

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR MODEL