> 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/copilot-assistant/copilot-assistant.md).

# Overview

Explore your BuildingPro Suites data with natural-language questions and explainable, data-grounded results.

Copilot Assistant is a natural-language interface for exploring asset and operational data in ABB Ability™ BuildingPro Suites. It helps you ask questions about your tenant's buildings, assets, measurements, and alarms without writing database queries.

Copilot Assistant is available in different licensing contexts. See [Access and Trial](/collection/copilot-assistant/access-and-trial.md) before you start.\
Additional Information for making the assistant much more useful, by preparing the asset structure and structure of their data as well as prompting practices, can be found in [Improving Results](/collection/copilot-assistant/improving-results.md) .

## What It Does

You can use Copilot Assistant to:

* Ask ad-hoc questions about assets and their current or historical data
* Analyse building and portfolio performance conversationally (e.g., compare buildings, locations, assets, or time periods)
* Accelerate decision-making through simplified access to complex operational data
* Receive results as tables, KPI cards, and charts

## How It Works

Requests are processed by a specialized agent. The agent resolves the concepts in your query against your project's asset model, executes the necessary data queries, analyses the results, and returns them in a structured format and visualisations. Users do not need to write queries or understand the underlying data structure.

▷ See [Data Agent](/collection/copilot-assistant/agent-modes/data-agent.md) for a detailed description of how requests are processed

▷ The [Academy AI documentation](/collection/academy/building-intelligence-ai-and-machine-learning-in-buildingpro-suites/agents.md) explains the underlying agentic concepts in more detail.

## What It Enables

As portfolios grow and integrate larger numbers of assets, navigating and analyzing all of this data manually becomes increasingly complex. \
Building a dashboard first or using the [Script Engine](/collection/platform/platform-core/script-engine.md) to bring data into the desired format takes time and requires technical knowledge that most business users do not have. \
This module removes that barrier. Instead of retrieving raw data manually, users can explore buildings and portfolios conversationally - asking questions in plain language the same way they would ask a data analyst.

## What It Is Not

Copilot Assistant is an analytical assistant grounded in the assets and data available to you. It is not a general-purpose chatbot and it does not replace professional judgment, it only accelerates retrieval and exploration so users can reach insights faster. The quality of an answer depends a lot on the structure, meaning, freshness, and coverage of the underlying data.

## Start Here

1. Review [Access and Trial](/collection/copilot-assistant/access-and-trial.md).
2. Check [Improving Results](/collection/copilot-assistant/improving-results.md).
3. Follow the [Quick Start](/collection/copilot-assistant/quick-start.md).
4. Review [Typical Use Cases](/collection/copilot-assistant/use-cases.md).


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.buildings.ability.abb/collection/copilot-assistant/copilot-assistant.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.