Orgis (Organised Real-time Global Inbox System)

Orgis unifies messages from WhatsApp, Telegram, Discord, Slack, email and more into one dashboard. It summarizes, prioritizes, and lets you act in one place—manage decisions, not apps.

Comment 1

Inspiration

  • Orgis started from a personal frustration—constantly switching between WhatsApp, Telegram, Discord, Slack, and email just to figure out what needed a reply first. It felt messy, stressful, and easy to miss important messages.
  • To validate this, we created a Google Form and discovered that many others faced the same issue of message overload and scattered communication. That’s when we realized this wasn’t just a personal problem, but a widespread one worth solving.

What it does

  • Orgis turns messages from multiple platforms into one unified inbox. It summarizes each message, assigns a priority (Act now, Review soon, For later), explains why, and lets users reply—all in one place.

How we built it

  • We built Orgis using Next.js, TypeScript, and MySQL, integrating with Beeper’s API to pull messages across platforms.
  • We used the Vercel AI SDK + OpenAI for structured triage, validated outputs with Zod, and added fallback heuristics to ensure reliability even without an API key.

Challenges we ran into

  • One key challenge was fine-tuning the AI prompts to correctly identify the priority and category of messages.
  • Small changes in wording could significantly affect classification, so we iterated heavily on prompt design, structured outputs carefully, and validated results to ensure consistent and reliable triage across different message types.

Accomplishments that we're proud of

  • We built a fully working cross-platform inbox with real-time syncing, AI-powered prioritization, and actionable workflows.
  • The ability to not just summarize but explain why something is urgent is a key highlight.
  • We also implemented multi-line message grouping, allowing the system to combine related messages into one unit—improving accuracy while reducing AI usage cost.

What we learned

  • We learned that good AI products aren’t just about generation—they’re about decision support.
  • Structuring AI outputs, handling messy real-world data, and focusing on user workflows made the biggest difference.

What's next for Orgis (Organised Real-time Global Inbox System)

  • We plan to improve personalization (e.g. smarter priority preferences), add more integrations beyond Beeper, and refine the AI to better understand user context over time.
  • We’re also expanding into mobile push notifications and bulk group-chat analysis to provide deeper insights across high-volume conversations.

Built With

Share this project:

Updates