Skip to main content

Finance Graph Generator Agent

Purpose​

Generate financial insight visualizations (PNG graphs) from merged transaction data, with automatic validation that required graphs were created.

Self-Validation​

Uses Stop hook to validate:

  • Assets directory exists
  • Minimum 5 PNG graphs generated
  • All required graph types present

Workflow​

  1. Read merged transactions CSV
  2. Analyze data for visualization opportunities
  3. Generate Python script using matplotlib/seaborn
  4. Execute script to create PNG files
  5. Validate (automatic via Stop hook) - blocks if graphs missing

Standard Graphs (8 Required)​

#GraphDescription
1plot_01_spending_by_category_pie.pngPie chart of spending by category
2plot_02_daily_spending_trend.pngLine chart of daily spending
3plot_03_income_vs_expenses.pngBar chart comparing income/expenses
4plot_04_top_merchants.pngBar chart of top merchants by spend
5plot_05_category_over_time.pngStacked area chart by category
6plot_06_running_balance.pngLine chart of account balance
7plot_07_spending_distribution.pngHistogram of transaction amounts
8plot_08_spending_by_weekday.pngBar chart by day of week

Usage​

Use finance-graph-generator agent to create visualizations for data/january/agentic_merged_transactions.csv
Use finance-graph-generator agent to generate graphs in assets/ directory

Output Structure​

target_directory/
└── assets/
    ├── plot_01_spending_by_category_pie.png
    ├── plot_02_daily_spending_trend.png
    ├── plot_03_income_vs_expenses.png
    ├── plot_04_top_merchants.png
    ├── plot_05_category_over_time.png
    ├── plot_06_running_balance.png
    ├── plot_07_spending_distribution.png
    └── plot_08_spending_by_weekday.png

Python Dependencies​

The generated script requires:

  • pandas
  • matplotlib
  • seaborn (optional, for enhanced styling)

Graph Styling​

All graphs follow consistent styling:

  • Professional color palette
  • Clear axis labels
  • Descriptive titles
  • Legend where appropriate
  • High DPI (150) for quality

Error Handling​

On validation failure:

  • Agent identifies which graphs are missing
  • Regenerates failed graphs
  • Re-validates until all graphs present

Core Responsibilities​

  • Analyze and assess pcf-products requirements within the PCF Products & Services domain
  • Provide expert guidance on finance graph generator best practices and standards
  • Generate actionable recommendations with implementation specifics
  • Validate outputs against CODITECT quality standards and governance requirements
  • Integrate findings with existing project plans and track-based task management

Capabilities​

Analysis & Assessment​

Systematic evaluation of pcf-products artifacts, identifying gaps, risks, and improvement opportunities. Produces structured findings with severity ratings and remediation priorities.

Recommendation Generation​

Creates actionable, specific recommendations tailored to the pcf-products context. Each recommendation includes implementation steps, effort estimates, and expected outcomes.

Quality Validation​

Validates deliverables against CODITECT standards, track governance requirements, and industry best practices. Ensures compliance with ADR decisions and component specifications.

Invocation Examples​

Direct Agent Call​

Task(subagent_type="finance-graph-generator",
     description="Brief task description",
     prompt="Detailed instructions for the agent")

Via CODITECT Command​

/agent finance-graph-generator "Your task description here"

Via MoE Routing​

/which Self-validating agent that generates financial insight visua