Skip to content

AbhishekGupta-193/Schedulify_CapstoneProject

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

6 Commits
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

πŸ€– Schedulify β€” AI Concierge for Workday Automation

A Multi-Agent AI System that autonomously manages meetings, inbox, reminders, and tasks β€” giving professionals back their precious time.


πŸ“Œ Introduction

Workplace AI has evolved from passive chatbots to autonomous systems capable of reasoning, collaborating, and taking actions.
Schedulify explores this next phase β€” an AI Concierge that understands context, makes decisions, and automates workflows end-to-end instead of merely answering questions.


🚨 Problem Statement

Modern professionals drown in:

  • endless inbox threads
  • scattered tasks
  • manual scheduling
  • forgettable reminders and deadlines

These repetitive chores silently waste hours every week, fragment focus, and reduce productivity.

Schedulify solves this by taking over administrative burden through an intelligent AI agentic workflow.
It can:

  • summarize long inbox messages
  • extract actionable tasks
  • detect and store reminders
  • check calendar availability & schedule meetings
  • maintain structured action logs

By behaving like a reliable personal assistant that never forgets, Schedulify frees users to focus on high-impact work.


🧠 Overview & Novelty

Schedulify is not a single assistant β€” it is a multi-agent collaboration system orchestrated to behave like a digital workforce.

🧩 Specialized Agents

Agent Capability
Summarization Agent Condenses long inbox messages
Scheduling Agent Checks availability, resolves conflicts, creates calendar events
Task Extraction Agent Converts unstructured text into actionable to-do lists
Reminder Agent Detects deadlines and creates reminders
Logging Agent Maintains structured logs for full transparency

Instead of rigid if-else workflows, Schedulify uses:

  • Natural language understanding
  • Multi-step LLM reasoning
  • Tool-calling
  • Shared memory and state continuity

This orchestration enables the system to adapt fluidly to messy, real-world conversations.


🧰 Technology Stack

Component Technology
Programming Language Python
LLM Google Gemini (via Google ADK)
Agent Framework Google ADK (Agent / Sequential / Parallel / Loop Agents)
Memory InMemorySessionService
Tools Inbox, Calendar, Reminder, Logging (Dummy Stores)
Architecture Modular and extensible β€” ready for integration via MCP

πŸš€ Vision & Future Scope

Schedulify is designed for real-world expansion:

  • πŸ”— Connect to Gmail / Outlook inbox
  • πŸ“… Sync with Google Calendar / MS Calendar
  • 🧾 Export reminders to task platforms (Notion, Todoist, ClickUp)
  • 🧠 Multi-model agent teams with reasoning feedback loops
  • πŸ›‘οΈ Enterprise-grade authentication and permissions

🏁 Conclusion

Schedulify demonstrates that AI Agents can manage workdays just like real virtual assistants β€” remembering context, collaborating across workflows, and taking autonomous actions.

This project serves as a blueprint for the next era of workplace automation β€” where AI becomes a proactive partner, not just a conversational bot.


Agent Workflow Demonstration

Sequential Flow Demonstration

Sequential Flow

Orchestration Flow Demonstration

Orchestration Flow

Session Management Demonstration

Session Management

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •