# Prism AI

> An agent inside the IDE that reads your open tab and your schema, dry-runs the SQL it writes, and edits the query in place, with your approval by default. It costs credits from your monthly allowance, or runs on a subscription you already have.

Source: https://docs.querylab.io/prism-ai/introduction/

**right panel**

**Prism**

<div class="chat" style="padding:0">
      <div style="text-align:center;padding:28px 0 18px">
        <div style="font-size:15px;font-weight:600;color:var(--ink)">
          Prism AI
        </div>
        <div style="font-size:12.5px;color:var(--ink-2);margin-top:4px">
          Your SQL assistant for BigQuery
        </div>
      </div>
      <div style="display:flex;flex-direction:column;align-items:center;gap:8px;margin-bottom:24px">
        <span class="btn outline sm">What can Prism do?</span>
        <span class="btn outline sm">Optimize my query</span>
        <span class="btn outline sm">Explain this query</span>
        <span class="btn outline sm">Help me write a query</span>
      </div>
      <div class="chat-in">
        Plan, @ for context, / for commands <span class="mode">Approve</span>
        <span class="mode">auto</span>
      </div>
    </div>

A fresh conversation. The four buttons are ready-made prompts; the input takes @ mentions and / commands.

## Opening it

`⌘`
`I` (`Ctrl`
`I` on Windows and Linux) toggles the panel, and so does the triangle
icon in the top bar. The panel header has **New conversation**, **Conversation
history**, **Settings**, and a credit counter such as `87/100`.

The header also shows the **attached tab**: the tab the agent reads from and writes to. It follows the active tab; click it to pin a different one.

- Signed in, or in the [Playground](https://docs.querylab.io/getting-started/playground/) (10 requests     a day there)
  - Settings → AI Features → **Enable Prism AI Features** is on (it is by     default)

## What it can see

Nothing until you ask. Each message carries the mode, the attached tab, and whatever you attach with `@`:

| Mention                                          | What goes to the model                                       |
| ------------------------------------------------ | ------------------------------------------------------------ |
| `@project.dataset.table`, `@dataset`, `@project` | Schema metadata: columns, types, partitioning. No rows       |
| `@graph`                                         | A property graph's labels, properties, node and edge tables  |
| `@Tab name`                                      | That tab's SQL and its last job (bytes, cost, duration)      |
| `@Tab name` under **Results**                    | The result's schema and row count; rows only if you allow it |

Beyond that the agent uses [tools](https://docs.querylab.io/prism-ai/features/) to look things up on its own: it can browse the schema, read tabs, validate SQL with a dry run, and read BigQuery's documentation; none of which needs confirmation. Anything that scans data or changes a tab is governed by the [mode](https://docs.querylab.io/prism-ai/modes/).

## What it can do

- Write a query from a description, or change the one in the attached tab, as a diff you apply or reject.
- Run `SELECT` queries and show the result in the chat. `INSERT`, `UPDATE`, `DELETE`, and DDL are rejected before they reach BigQuery.
- Explain, debug, and optimize: it validates its own SQL, sees the dry-run estimate, and knows about partition and cluster columns.
- Sample a table's data at no cost, draw a chart, create tabs and notebook cells, search your saved queries.

> **It can be wrong.** The agent dry-runs what it writes, so syntax errors are rare; wrong joins and   wrong assumptions are not. Read the diff before you apply it.

## Where your data goes

Messages, attached SQL, and schema metadata are sent through Querylab.io's backend to the provider you chose. Conversations are saved so you can resume them.

Query **results** are the exception. By default the agent runs a query and sees only its schema and row count. The panel says _AI cannot see query results — only the schema is shared_ and offers **Share with AI** per result. Settings → AI Features → **Share Query Results Preview** has three values:

| Value                   | Behaviour                                                      |
| ----------------------- | -------------------------------------------------------------- |
| Disabled (never share)  | Rows never leave the browser                                   |
| Ask each time (default) | A **Share Query Results?** dialog, with **Remember my choice** |
| Always allow            | Rows are shared without asking                                 |

The same setting covers table samples.

On the desktop app you can bypass Querylab.io's backend entirely and run the agent through a CLI you already have installed, or on your own API key; see [CLI integration](https://docs.querylab.io/prism-ai/cli-integration/).

## Models and credits

The model dropdown next to the mode selector lists **Querylab.io Cloud** models and, on desktop, **Your Subscriptions**. **Auto** picks a model per message; its cost shows as _varies_. Every other model shows a multiplier (`1x`, `7x`), which is the credits one message costs. Every account gets a monthly credit allowance; the counter in the panel header and Settings → AI Features → **AI Providers** show what's left and when it resets.

The model is fixed for the length of a conversation. To change it, start a new one.