> For the complete documentation index, see [llms.txt](https://docs.buildings.ability.abb/collection/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.buildings.ability.abb/collection/english-v14/getting-started/kunstliche-intelligenz-in-abb-buildingpro.md).

# Artificial intelligence in ABB BuildingPro

## **Why AI in building operations?**

Modern buildings are no longer rigid concrete shells – they are complex, interconnected systems with thousands of sensors, actuators, and control logics. This infrastructure continuously generates large volumes of data on energy consumption, room climate, occupancy, and system status.

Despite this wealth of data, many optimization opportunities remain unused. Typical causes:

* **Rigid control systems** – classic time schedules or PID controllers respond only to current measured values, not to historical patterns or forecasts.
* **Growing demands** – volatile energy prices, CO₂ requirements, and changing usage patterns increase the pressure.
* **Difficult data access** – relevant measured values often have to be painstakingly searched for and analyzed, usually only by SQL experts.

## **The AI framework from** ABB BuildingPro

ABB BuildingPro addresses these challenges with an integrated **AI framework**, which combines three key technologies:

### **Reinforcement Learning (RL)**

Self-learning optimization of systems such as HVAC, lighting, or storage systems. The RL agent learns from live and historical data in order to optimally balance costs, energy, and comfort.

{% content-ref url="/pages/45f0dfb6968a4744f6e01df1910b4896f659e9ec" %}
[Reinforcement Learning](/collection/english-v14/getting-started/kunstliche-intelligenz-in-abb-buildingpro/reinforcement-learning.md)
{% endcontent-ref %}

### **Forecasting**

Precise forecasts for energy consumption, peak loads, room climate, and occupancy in order to proactively control operating strategies.

{% content-ref url="/pages/d1e1573e177a555059a6d4f57e182e28c3184488" %}
[Forecasting](/collection/english-v14/getting-started/kunstliche-intelligenz-in-abb-buildingpro/forecasting.md)
{% endcontent-ref %}

### **Large Language Models (LLM)**

Natural language queries instead of complex SQL commands. LLMs know all assets and data points and deliver results as tables, charts, or reports.

{% content-ref url="/pages/c8aa91e51507918cab5c66f0ea2e033859fd4da3" %}
[NL2SQL](/collection/english-v14/getting-started/kunstliche-intelligenz-in-abb-buildingpro/nl2sql.md)
{% endcontent-ref %}

## **AI orchestration with rule chains**

In ABB BuildingPro, **rule chains** serve as the central orchestration platform for all AI modules:

* **Combine models** – e.g. link forecast data with RL optimizations.
* **Automatic start & stop** – activate AI modules only when they deliver value.
* **Safety logic** – automatically detect and stop unwanted actions by AI agents.

This creates a **autonomous, predictive, and secure building operation**, that saves energy, smooths peak loads, and guarantees comfort – with full transparency and control.

{% content-ref url="/pages/47f8cc2ca8c15dfb55680fed3476bcc177db191b" %}
[AI orchestration in ABB BuildingPro](/collection/english-v14/getting-started/kunstliche-intelligenz-in-abb-buildingpro/ki-orchestrierung-in-abb-buildingpro.md)
{% endcontent-ref %}

{% hint style="success" %}
The functions and scenarios described here show the potential of AI-supported building automation with ABB BuildingPro. Some of them are still under development or are designed as a vision for the future. Our goal is to realize these possibilities step by step so that you will soon have access to the full range of intelligent, self-optimizing building control.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.buildings.ability.abb/collection/english-v14/getting-started/kunstliche-intelligenz-in-abb-buildingpro.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.