Overview
Expert Center pairs an AI agent with targeted human expertise to turn a building's raw data into an enriched building model.
Everything lives under an organization → building hierarchy. Each building has one or more connectors: integrations that bring a source system's data, such as a BMS, into Mapped as raw entities. Expert Center pulls a building's entities in from the Mapped graph and pushes the enriched model back. Enrichment turns those raw entities into an integrated, normalized building model representing the real world. This is achieved through an iterative, human-in-the-loop workflow: experts describe a small part of the building, an AI agent they talk to in chat generalizes that description into rules, and experts review what those rules produce. A few labels typically carry most of a building and rules do the rest.
Three things drive that loop:
| Concept | What it is | Who creates it |
|---|---|---|
| Entity | A point, device, space, or other instance in the building, plus its metadata. | Connectors, rules, or experts |
| Label or instruction | Expert knowledge of the building, and how they want an entity's data interpreted. A label is a fact asserted on one entity. An instruction is the same knowledge in plain language, with no entity attached. | Experts |
| Rule | A condition that matches entities and an action that enriches them. A single rule enriches every entity it matches. | The agent, from labels and instructions |
The Loop
- Label. Experts label a fraction of the building. A label is a fact asserted on one entity, and it is its own approval: it never has to be reviewed.
- Infer. The agent turns each label, or each instruction, into a rule and proposes how far it reaches. Every rule must satisfy the labels it was generated from. The agent runs the rule against them, then checks and revises it.
- Review. Experts approve or reject rules. Approving a rule approves everything it produced at once. When a rule produces something that does not belong, the expert flags it as a false positive. That flag is feedback: the agent narrows the rule's condition to exclude it and checks the rule against its labels again.
- Repeat. The cycle starts again where the rules did not reach.
Three Kinds of Enrichment
| Kind | What it does | Example |
|---|---|---|
| Classification | Assigns a type and/or unit to an entity | This point is a Zone Air Temperature Sensor, °F |
| Reification | Creates a new entity derived from an existing one | This point implies the equipment VAV101 |
| Link | Declares a relation between two entities | VAV101 has point VAV101_ZNT |
Each kind can appear as a label (one entity, set by an expert) or a rule (many entities, generated by the agent).
A Concrete Example
A BMS connector contains a point named VAV101_ZNT. An expert labels it:
- Classification: this is a Zone Air Temperature Sensor, from the metadata in its name and its observed unit of °F.
- Reification: the metadata implies equipment VAV101 that does not exist yet; reification creates it.
- Link: VAV101, the newly created equipment, has point VAV101_ZNT.
The agent turns each label into a rule. The classification rule matches every entity whose name ends in _ZNT and tags it the same way. One label, hundreds of enriched entities.
How the Pieces Connect
- A label is made on one entity. The agent reads it and generates a rule of the matching kind. The rule records which labels and entities it came from.
- An instruction is given to the agent in plain language. The agent transcribes it directly into rules.
- A rule's condition matches entities across the building; its action enriches each match. Everything a rule adds, such as a new piece of equipment, a relation or a type, is listed as one of its outputs, for you to review.
- An output is approved when a rule that produced it is approved, or when a label states the same thing. It stays pending while a rule that produced it is still under review, and is declined once every rule that produced it is rejected.
Unification
Several entities can describe the same real-world thing, for example one air handler seen through two connectors. Experts group them under one canonical entity, which gives the group its name and type, so the final building model has one entity per real-world thing.
Next Steps
- Getting Started: how to open Expert Center from the Console, what you do there, and where to find the help built into the app.