> ## Documentation Index
> Fetch the complete documentation index at: https://netter.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Assistant

> Netter's chat assistants answer questions, model your ontology, and build apps. Each chat works by calling tools—and every tool respects your permissions.

Most of what you do in Netter, you can do by chatting. The same assistant powers several surfaces, each with a different job and a different set of **tools** it's allowed to call.

## The chats

| Chat                | Where               | What it does                                                                                                                 |
| ------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------------------------- |
| **Ask Netter**      | The assistant page  | Answers questions about your data and composes charts and KPIs. Read-only.                                                   |
| **Ontology design** | The ontology editor | Creates and edits entities, fields, and relationships through conversation.                                                  |
| **App design**      | The app editor      | Designs viewer-facing apps—proposes which entities they read and write, and what actions they expose.                        |
| **Pipeline**        | Inside a project    | Builds a [pipeline](/docs/pipelines/quickstart) from steps and pre-coded operators, wires the graph, and tests it on sample data. |
| **Workflow**        | The workflow editor | Builds a trigger-driven workflow—a graph of nodes fired by a schedule, an entity change, or an app button.                   |
| **Dashboard**       | A dashboard         | Edits a dashboard through chat.                                                                                              |

You can also open a chat scoped to a project, dashboard, or a single app widget; it carries that context into the conversation.

## How a chat uses tools

The assistant doesn't answer from thin air. It calls **tools**—small, named operations like "list the entities," "search the databases," or "add a field to this entity." It chains several tool calls to get your answer or make your change.

You can watch this happen. Each assistant message has a **Netter is thinking…** line you can expand to see the timeline: its reasoning interleaved with the tool calls it made, each shown with an icon, a name (`list_entities`, `Edit`, `describe_entity`), and what it acted on. Nothing is hidden—the tool activity is right there in the transcript.

## Tools respect your permissions

This is the important part: **the assistant acts as you, not above you.**

* Tools that return data—answers, charts, search results—apply your resource access and [row-level security](/docs/permissions/row-level-security). The assistant can't surface a row, dataset, or entity you couldn't open yourself.
* Tools that change things—creating an entity, editing fields, promoting a database—check the same permission levels the equivalent buttons do. If you lack the level, the tool refuses and the assistant tells you why instead of doing it anyway.

A full breakdown of every tool and the permission it requires is in [Chat tools](/docs/assistant/tools).

## Next

* [Chat tools](/docs/assistant/tools) — the complete tool list and the permission each one respects.
* [Permissions](/docs/permissions/overview) — the access model the tools enforce.
* [Build an app](/docs/applications/build) — design a viewer surface through the app chat.