> For the complete documentation index, see [llms.txt](https://docs.myrspoven.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.myrspoven.com/ai-features/ai-freedom.md).

# AI Freedom

AI Freedom is an umbrella setting in myCoreAI that lets the optimizer pursue energy savings more aggressively by relaxing how strictly configured comfort bounds and schedules are enforced. Enabling it activates two underlying behaviors together: learned reference comfort bounds, and a guaranteed setback during unoccupied hours.

## What it does

* **Indoor climate baseline.** myCoreAI replaces static min/max comfort bounds with learned reference bounds derived from the building's actual performance. Office hours retain bounds close to the configured limits; non-office hours widen them further. See [Indoor climate baseline](/ai-features/indoor-climate-baseline.md).
* [**Comfort schedule**](/ai-features/comfort-schedule.md). AI Freedom enables Automatic Comfort Schedule (ACS) with a guaranteed setback. During unoccupied periods, myCoreAI widens comfort bounds by at least 0.5 °C.

## How it works

| Value | Effect                                                        |
| ----- | ------------------------------------------------------------- |
| Off   | myCoreAI stays within configured static bounds and schedules. |
| On    | Both underlying behaviors activate together.                  |

In customer-facing terms, treat AI Freedom as on/off: any value above zero activates it fully, with no partial levels. Each underlying feature can also be enabled independently of AI Freedom. The umbrella turns both on at once.

## Scope

AI Freedom relies on enough history for the learned reference bounds to be meaningful. Reasonable to enable when:

* The building has been monitored for several months and behavior is stable.
* Occupancy patterns are predictable enough for a learned schedule to be trustworthy.
* Energy savings are prioritized over the tightest possible comfort bounds.

Reasonable to leave off (or turn off) when:

* The building is new to myCoreAI or has just been renovated.
* Comfort complaints are still being root-caused.
* The building is in a commissioning or validation period that requires predictable, configuration-driven behavior.

## Worked example

An office building with stable occupancy enables AI Freedom after six months of monitoring. myCoreAI replaces the configured 21–23 °C comfort bounds with learned reference bounds: 21.2–22.8 °C during weekday office hours, and 19.5–24.5 °C overnight and weekends. During unoccupied periods, the guaranteed 0.5 °C setback ensures the optimizer can coast on stored thermal mass rather than holding daytime setpoints. Heating energy drops without daytime comfort complaints.

## Interaction with other settings

AI Freedom changes which comfort bounds myCoreAI uses and guarantees a minimum unoccupied-hours setback. It does **not** override:

* Hard guardrails and crash protections.
* Maximum rate-of-change limits on heating circuits.
* Other building-specific limits unrelated to comfort min/max.

When a comfort complaint arrives with AI Freedom on, the first diagnostic step is to compare the learned reference bounds against the configured comfort bounds and check whether the learned bounds are wider than intended.


---

# 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.myrspoven.com/ai-features/ai-freedom.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.