Skip to content

enayas/wehack26

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

40 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Miro — wehack26

Upload the past, Mirror the present.

Property managers don’t just manage buildings, they manage layers of history.

Miro is a memory system for property managers that transforms scattered operational data—emails, spreadsheets, and tenant history—into a living intelligence layer. It ensures that institutional knowledge does not get lost when people leave, but instead becomes instantly usable context for anyone managing a portfolio.

Miro changes how institutional memory is handled in commercial real estate. When a property manager leaves, critical context is often fragmented across tools and incomplete handoffs, forcing the next manager to rebuild understanding from scratch. Miro solves that gap by preserving and mirroring the past into the present. So whether it’s a new manager stepping in or a current one managing day-to-day operations, they aren’t starting from zero, they’re always working with the full context of everything that came before.

Problem

Property managers do not just manage buildings—they manage layers of history.

In commercial real estate, critical context is spread across email threads, spreadsheets, and individual memory. When a property manager leaves, that knowledge is often fragmented or lost in transition, forcing the next person to rebuild understanding from scratch.


Solution

Miro preserves and mirrors institutional memory into the present.

It turns fragmented data into a structured, queryable intelligence system that gives property managers full context on day one rather than after months of onboarding.


Features

  • Email ingestion (Gmail) — full thread context, not isolated messages
  • Spreadsheet integration (Google Sheets) — structured operational data extraction
  • AI memory layer — converts unstructured data into tenant and property intelligence
  • Risk detection — identifies tenant risk, maintenance patterns, and escalation signals
  • Daily briefing — ranked overview of what matters each morning
  • Portfolio heatmap — visual risk and activity mapping across properties
  • Ranked tenant table — sortable insights based on urgency and history
  • Multimodal analysis — upload maintenance images for AI-driven assessment

Tech Stack

  • Frontend: React
  • Backend: FastAPI
  • AI: Gemini API
  • Auth and Ingestion: Google OAuth (Gmail and Sheets)
  • Memory Layer: Supabase with pgvector (RAG-based retrieval)
  • Processing: LLM-based structured extraction pipeline

How it works

  1. Users connect Google Workspace (Gmail and Sheets)
  2. Miro ingests full email threads and spreadsheet data
  3. Gemini extracts structured memory (tenants, risks, events, context)
  4. Data is stored in a vector database for semantic retrieval
  5. A RAG-based agent enables natural language queries
  6. Dashboard surfaces insights through:
    • Daily briefing
    • Heatmap view
    • Ranked tenant table

Key insight

The hardest part of building AI systems is not generating information, but deciding what matters.

Miro focuses on turning raw data into prioritized, contextual intelligence that helps users act, not just read.


Future work

  • Deeper integrations with property management systems such as Yardi and MRI
  • Predictive risk modeling for tenants and maintenance issues
  • Shared organizational memory across teams
  • Expanded multimodal inputs including documents, photos, and voice

Tagline

Upload the past, Mirror the present.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors