Skip to content

ada-ggf25/Auto-Calendar-Agent

Β 
Β 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

35 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

alt text

Logo AI Challenge 2025 | Auto Calendar Deadline Manager Agent Challenge


πŸš€ Developed Solution: AI-Powered Deadline Manager

πŸ“‹ Solution Overview

This repository contains a production-ready AI-powered deadline management system specifically designed for Portuguese tax professionals. The solution processes multi-modal documents (PDFs, DOCX, images, handwritten notes) and automatically extracts tax-related deadlines using advanced AI and Portuguese tax law compliance rules.

🎯 Key Features

  • πŸ€– AI-Powered Processing: Dual AI model support (Google Gemini Pro & Flash) for intelligent deadline extraction
  • πŸ“„ Multi-Modal Document Support: PDFs, DOCX, JPEG, PNG, and handwritten notes
  • βš–οΈ Portuguese Tax Law Compliance: Built-in rules for CPPT, CPA, and Portuguese holiday calendars
  • πŸ“… Smart Date Inference: Handles implicit deadlines ("5 business days from notification")
  • πŸ’° Business Value: €99,970 annual value through 76.9% automation success rate
  • 🎨 Modern Web Interface: Interactive Streamlit application with calendar visualization
  • πŸ“Š Analytics Dashboard: Processing statistics and performance metrics

πŸ—οΈ Repository Structure

ey-deadline-manager/
β”œβ”€β”€ src/ey_deadline_manager/           # Main package
β”‚   β”œβ”€β”€ app/                           # Streamlit web application
β”‚   β”‚   └── streamlit_app.py          # Main web interface (1,247 lines)
β”‚   β”œβ”€β”€ core/                          # Core business logic
β”‚   β”‚   └── deadline_agent_backend.py # AI processing engine (557 lines)
β”‚   β”œβ”€β”€ models/                        # Data models
β”‚   └── utils/                         # Utility functions
β”œβ”€β”€ tests/                             # Comprehensive test suite
β”‚   β”œβ”€β”€ test_agent.py                 # Core logic tests
β”‚   └── test_streamlit_app.py         # Application tests
β”œβ”€β”€ data/                              # 26 test documents (PDFs, DOCX, images)
β”œβ”€β”€ notebooks/                         # Development notebook
β”‚   └── AutoCalendarAgent.ipynb       # Google Colab compatible
β”œβ”€β”€ config/                            # Configuration management
β”‚   β”œβ”€β”€ .env.example                  # Environment template
β”‚   └── .pre-commit-config.yaml       # Code quality hooks
β”œβ”€β”€ scripts/                           # Development workflow
β”œβ”€β”€ docs/                              # API documentation
└── reports/                           # Business reports & metrics

πŸ”§ Technical Architecture

AI Processing Pipeline

  1. Document Ingestion: Multi-format support with OCR for images
  2. Text Extraction: Advanced parsing for structured/unstructured content
  3. AI Analysis: Dual-model processing with Google Gemini
  4. Rule Application: Portuguese tax law compliance engine
  5. Date Calculation: Working days with Portuguese holidays
  6. Output Generation: Structured deadline information

Core Technologies

  • Backend: Python 3.10+ with modern packaging (UV)
  • AI Models: Google Gemini Pro & Flash
  • Web Framework: Streamlit for interactive interface
  • Document Processing: PyPDF2, python-docx, Tesseract OCR
  • Date Handling: Custom Portuguese calendar with holidays
  • Code Quality: Ruff linting, pre-commit hooks, comprehensive tests

πŸ“ˆ Demonstrated Results

  • βœ… 26 test documents processed successfully
  • βœ… 76.9% success rate in deadline extraction
  • βœ… €99,970 annual business value calculated
  • βœ… Production-ready code with 4,008+ lines
  • βœ… Portuguese tax compliance validated
  • βœ… Multi-modal processing including handwritten notes

πŸš€ Quick Start

Installation & Setup

# Clone repository
git clone <repository-url>
cd Auto-Calendar-Agent

# Install dependencies
make dev-install

# Configure environment
cp config/.env.example config/.env
# Edit .env with your Google API key

# Run application
make run

Using the Application

  1. Upload Documents: Drag & drop PDFs, DOCX, or images
  2. AI Processing: Automatic deadline extraction with Portuguese tax rules
  3. Calendar View: Visual deadline management with analytics
  4. Export Results: Download processing results and analytics

πŸ’Ό Business Value Proposition

For Tax Professionals

  • Time Savings: 76.9% automation reduces manual processing
  • Risk Reduction: Compliance with Portuguese tax deadlines
  • Efficiency Gains: Process 26 documents in minutes vs. hours
  • Error Prevention: AI-powered validation and cross-checking

For EY Consulting

  • €99,970 annual value per tax professional
  • Scalable solution for multiple clients
  • Modern tech stack with production deployment
  • Competitive advantage in tax technology services

πŸ› οΈ Development Workflow

# Development commands
make dev-install    # Install all dependencies
make run           # Start Streamlit application
make test          # Run comprehensive test suite
make lint          # Code quality checks
make format        # Auto-format code

πŸ“Š Performance Metrics

  • Processing Speed: ~2-3 seconds per document
  • Success Rate: 76.9% automated deadline extraction
  • Accuracy: 95%+ for Portuguese tax compliance
  • Document Types: PDF (70%), DOCX (20%), Images (10%)
  • Business Impact: €99,970 annual value per user

🧠 Original Challenge Description

Problem Statement

In this challenge, your team will support Tax Service client by designing an AI-powered agent capable of managing and interpreting deadlines from diverse input channels.

Tax professionals regularly receive time-sensitive obligations through various means:

  • Scanned letters from tax authorities
  • Client emails
  • WhatsApp messages
  • SMS
  • Handwritten notes
  • [...]

Your goal is to develop a solution that can ingest multimodal inputs, extract or infer relevant deadlines, and produce structured output to enhance:

  • Operational efficiency
  • Risk reduction
  • Regulatory compliance

Many real-world deadlines are not explicitly stated. For example:

β€œYou must reply within 5 business days from the date of this notification.”

Your AI agent must:

  • Determine the base date
  • Apply Portuguese legal logic (e.g., CΓ³digo de Procedimento e de Processo TributΓ‘rio, CΓ³digo do Procedimento Administrativo)
  • Produce an accurate due date

This simulates a real consulting engagement where you must deliver both a prototype and a strategic pitch to showcase its business value.


πŸ—ƒοΈ Dataset

You will receive 26 multimodal inputs, including:

  • πŸ“„ scanned letters
  • βœ‰οΈ plain text emails
  • πŸ“± WhatsApp screenshots
  • ✍️ handwritten notes or scribbles

Each document contains explicit or implicit tax-related deadlines, often requiring nuanced interpretation.


🧭 Consulting Mindset Expectations

  • Legal Logic Designers
    Create a system that understands procedural rules and deadline logic from Portuguese tax law.

  • Multi-Modal Integrators
    Unify text, image, and possibly audio inputs to produce actionable intelligence.

  • Efficiency Catalysts
    Build tools that save time, reduce manual error, and streamline EY’s deadline management.

  • Strategic Communicators
    Present your solution as a business asset that can be adopted and scaled by tax professionals.


πŸ“¦ Deliverables

  • βœ… A working prototype of your AI-powered deadline assistant
  • βœ… Modular, clean, and well-documented code
  • βœ… A consulting-style presentation to EY executives
  • βœ… (Optional) (Optional) It’s a major plus if your presentation includes a brief live demo to showcase how the solution works in practice, you can even present over it.
  • βœ… (Optional) Provide metrics like:
    • ⏱ Average processing time
    • ❌ Error rate reduction
    • πŸ“š Legal coverage scope

⚠️ **Important Submission Requirement** ⚠️

βœ… Before the 14h00 deadline

Submit a zip folder with:

  • The Google Colab notebook (with all cells run & outputs shown)
  • Screenshots of any external tools or visualizations you used
  • Email it to: [email protected]
  • Subject: AutoCalendarDeadlineManagerAgent – GroupName
  • Include group member names in the email
  • πŸ“ Only one submission per group

πŸ’‘ Tips for Competitors

  • Understand the Business Challenge
    Research what types of obligations exist (e.g., notifications from AT), and how deadlines are calculated.

  • Design for Ambiguity
    Handle incomplete inputs, conflicting messages, and uncertainty

  • Combine Rule Engines + LLMs
    Combine deterministic logic (rules, calendars, holiday lookups) with natural language understanding.

  • Visualize Time
    Consider timeline visualizations like:

    • πŸ“… Calendar views
    • πŸ“Š Gantt charts
    • 🚨 Deadline alerts
  • Validate Relentlessly
    Address:

    • ❗ False positives
    • πŸ€– Mesread text
    • πŸ”„ Conflicting data sources

πŸ›  Tech & Tools

🚨 Mandatory:
It is mandatory to develop the solution in Google Colab using Python.

Other than that, you are completely free to choose your own:

  • πŸ”§ Libraries
    LangChain, Pandas, OCR(Tesseract), dateparser, calendar APIs, etc.

  • πŸ“ˆ Visualization Tools
    Streamlit, Dash, Power BI, etc.

  • πŸ€– AI Assistants
    ChatGPT, GitHub Copilot, Gemini, etc.

πŸ’₯ Use any tools that enhance speed, accuracy, or creativity


⏱ Time Management & Rules

  • ⏳ You have 4 hours to complete the challenge
    πŸ”’ No extensions

  • πŸ—£ Present your solution in a 5-minute pitch, simulating a client-facing demo

  • πŸ‘₯ Each group is allowed:

    • 1 technical support session (up to 5 minutes)
    • 1 business guidance session (up to 5 minutes)

🚫 Assistants won’t provide direct solutions
🧠 They’re here to help you think and overcome blockers


πŸ’¬ Final Thought

This challenge reflects a growing need in professional services: automating complexity. Your solution has the potential to not only increase compliance accuracy, but also free up human capital for higher-value tasks. Think like consultants β€” design something practical, strategic, and future-ready.


🏁 Brought to you by EY AI Challenge

About

EY AI Challenge 2025 | Auto Calendar Agent | #1 Place of the Category | #2 Place Ovear All

Topics

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Jupyter Notebook 66.7%
  • Python 31.0%
  • Shell 1.5%
  • Makefile 0.8%