UPLO
UPLO is an organisational digital twin for the era of AI teammates.
Core trick
Builds an organisational graph from connected Drive, Slack, email and GitHub data, and serves current directives to agents over an MCP server.
Description
UPLO is an organisational digital twin for the era of AI teammates. As AI agents join the workforce - not as tools but as team leads managing human reports — organisations need a way to steer the entire ship.
UPLO crawls your data sources (Google Drive, Slack, email, GitHub), builds a living interactive graph of your entire company, and gives leadership a directive system that cascades through both human and AI teams.
Every agent gets live organisational context via MCP so it never has to guess or hallucinate - it knows the current priorities, who's working on what, and which directives apply before it acts. Features include: 2D and 3D org visualisation, directive cascade with authority-level conflict detection, multi-model AI chat with full document context injection, communication alignment monitoring with auto-nudges, and an MCP directive server for agent compliance checking.
README excerpt
# UPLO — Organisational Digital Twin **[Live Demo](https://uplo-hackathon.vercel.app)** Built by **Andrew Jenkins** at Zero to Agent: Vercel x DeepMind Hackathon London — 21 March 2026. --- ## The Problem AI agents are joining the workforce — not as tools, but as team members. In modern organisations, AI agents serve as team leads managing human reports. But how do you steer a company where half the crew is autonomous? How do you make sure every agent knows the current priorities, isn't duplicating work, and isn't contradicting a directive from leadership? Today, organisations are invisible. Structure lives in spreadsheets, priorities live in Slack threads, and nobody has a single view of who's doing what. Add AI agents to that mix and you have autonomous workers making decisions without organisational awareness. ## The Solution UPLO makes your organisation visible. It crawls your data sources, builds a living graph of every person, agent, project, and document, and gives leadership a directive system that cascades through both human and AI teams — with real-time compliance checking. Every AI agent gets live organisational context automatically. They don't search for it. They don't guess. They don't hallucinate. The full directive chain, current priorities, and active work across the org is injected as context — so when an agent makes a decision, it's grounded in what's actually happening. ## What It Does **See your entire organisation as a graph** - Interactive 2D