> For the complete documentation index, see [llms.txt](https://docs.chirpwireless.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chirpwireless.io/ai-assistant/talking-to-your-home.md).

# Talking to Your Home

Just ask. There are no special commands to memorize and no query syntax to learn. Type the same way you would text a friend who happens to know everything about your house — whether you're *asking about* your home or *asking the helper to set something up*. This page is about asking questions; to hand it real jobs, see [Let the Helper Set It Up](/ai-assistant/let-ai-set-it-up.md).

## Tips for better answers

* **Mention the sensor or room by name.** "What is the kitchen temperature?" works much better than "What is the temperature?" when you have sensors in every room.
* **Be specific about time.** "Last night," "this morning," "past 3 days," "since Monday" — the helper understands everyday time expressions.
* **Ask follow-ups.** The helper remembers what you talked about earlier in the conversation. You can say "now show me the same thing for the garage" without repeating yourself.
* **Bring back your last message.** Tap the **Up arrow** key in the message box to pull up what you just sent, so you can tweak it and ask again.

## Example questions

### Right now

* "What is the bedroom temperature?"
* "Is the front door closed?"
* "Which sensors are offline?"
* "How much battery does the patio sensor have left?"

### Looking back

* "What was the garden humidity yesterday?"
* "When did the basement last get above 70 percent humidity?"
* "How many times did the back door open last weekend?"
* "What was the coldest reading from the wine cellar this month?"

### Charts

* "Show me a chart of living room temperature this week"
* "Graph the balcony humidity for the past 3 days"
* "Create a bar chart comparing all my temperature sensors today"

### Help with Chirp

* "How do I set up an automation?"
* "What does the alarm inbox do?"
* "How do I add a new sensor?"

## Building on a conversation

Because the helper keeps context within a session, you can refine your questions step by step:

1. "What was the bedroom temperature last night?"
2. "Compare that with the nursery"
3. "Show me both on a chart for the whole week"
4. "Were there any readings above 25 degrees?"

Each follow-up builds naturally on the last, turning a simple question into a detailed picture of what happened in your home.

## From asking to doing

The same chat can slide straight from a question into an action. After "how often did the basement get damp last week?" you can simply add "set up an alert if it happens again" — and the helper builds it for you. Whenever a request would change something that matters, it shows a **Confirm Action** / **Cancel** prompt first, so you're always the one who decides. See [Let the Helper Set It Up](/ai-assistant/let-ai-set-it-up.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 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.chirpwireless.io/ai-assistant/talking-to-your-home.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.