Mapped

The foundation for physical AI.

[Mapped @mapped]

Every connector we run, and which direction each one goes: https://t.co/0BcpTh4HoJ

[Mapped @mapped]

A work order closed at 4:00. The fault was still there at 5:00. Weeks later it's back with a new number.

What closes the loop is connecting the close-out to the readings that came after it.

#CMMS #PhysicalAI

[Mapped @mapped]

Watch episode 3 of One Day AI: https://t.co/DZY7wbYpC9

[Mapped @mapped]

Before AI goes to work in your buildings, IT will ask what happens to the data about people.

In One Day AI ep. 3, a simulated LAX runs landside and airside in one graph, with personal information stripped at the edge 🎥

#OneDayAI

[Mapped @mapped]

The four requirements in more detail: https://t.co/EcCLG12rT5

[Mapped @mapped]

A lot of 2027 budgets include AI for operations.

The work that has to happen first is easy to leave out: points that say what they are, equipment tied to spaces, history, and IDs that survive a controller swap.

#PhysicalAI

[Mapped @mapped]

Why Physical AI starts with a model of the real world: https://t.co/dn2D0Zfm86

[Mapped @mapped]

In heating season, the first sensor to report an overheated room is usually a person.

The thermostat, the schedule, and occupancy all knew first. They just weren't tied to the same room, and AI can't connect them until they are.

#PhysicalAI

[Mapped @mapped]

Watch episode 6: https://t.co/nJXVCYeYpx

[Mapped @mapped]

A radio call says the baggage hall feels stuffy. In episode 6 of One Day AI, a simulated facilities lead checks the CO2, confirms it’s a trend, and finds the nearest staff member in a few questions.

Full episode below.

#PhysicalAI #WorldModel #OneDayAI

[Mapped @mapped]

Here’s how to connect your assistant to the Mapped MCP: https://t.co/Xf9VKrSilM

[Mapped @mapped]

More building software ships with its own AI assistant, and each one only knows its own system. At NexusCon, owners told us they’d rather use one assistant and connect it to every vendor through MCP.

How is your team deciding which assistant to work in?

#PhysicalAI #WorldModel

[Mapped @mapped]

Our airport demos run in a simulated environment.
Here’s what it looks like live: at a major US airport, a partner built on Mapped to bring 170,000+ assets and 120,000+ live data points into one graph, targeting 20-25% lower maintenance costs by 2030.

#PhysicalAI #WorldModel

[Mapped @mapped]

More on how we apply this to location data in Jose de Castro’s Sensor Fusion blog: https://t.co/U2lVSVHiH0

[Mapped @mapped]

A sensor stops reporting at 2am. The dashboard keeps showing its last reading as if nothing changed. A person might catch it. An agent has no reason to doubt it.

How does your team decide when a reading is too stale to act on?

#PhysicalAI #WorldModel

[Mapped @mapped]

Watch episode 2 of One Day AI: https://t.co/y0UhzXxTTq

[Mapped @mapped]

A hot rack, the technician who could check it, and the inspection robot usually show up in three different systems.

In episode 2 of our new One Day AI video series, they’re in one 3D view of a simulated 1,000-rack data center 🎥

Watch (link in reply)

#PhysicalAI #OneDayAI

[Mapped @mapped]

We’re at CREtech New York! Find Shaun Cooley, Robert Goodman, and Donovan Fitch at Booth #326 at the Javits Center today and tomorrow. Come say hi 👋

#PhysicalAI #CREtech

[Mapped @mapped]

Read the full story: https://t.co/WRfZANg4Y6

[Mapped @mapped]

We gave Claude a model of a simulated airport. The ops dashboard took 10 hours. Then came an assistant inside it, and a simulated facilities manager to test it ✈️

Jose de Castro walks through the build (link in reply)

#PhysicalAI #OneDayAI