# Modes

> One dropdown in the chat input decides what the agent may do without asking. Readonly never touches your tabs, Approve shows every change as a diff first, Auto applies and runs on its own. The default is Approve.

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

**chat input → mode**

The selector sits at the left of the input. It's disabled while a response is streaming.

## What each mode permits

Reading never needs permission in any mode: the agent can inspect tabs, browse the schema, validate SQL with a dry run, sample a table, and read the BigQuery docs. The mode only gates the two things that cost money or change your work: scanning data and writing to a tab.

|                                       | Readonly                | Approve                 | Auto        |
| ------------------------------------- | ----------------------- | ----------------------- | ----------- |
| Read tabs, schema, docs; validate SQL | Yes                     | Yes                     | Yes         |
| Run a `SELECT`                        | After you click **Run** | After you click **Run** | Immediately |
| Edit SQL in a tab or cell             | Refused                 | Diff, then **Apply**    | Immediately |
| Create or rename tabs and cells       | Refused                 | Yes                     | Yes         |

The mode is sent with every message, so you can change it mid-conversation. Switch to Readonly while you explore, back to Approve when you want changes.

## Approve

An edit arrives as a pending diff in the attached tab. Nothing is written until you decide:

**Query 1 · pending edit**

```sql
SELECT vehicle_id, make, model, completed_date
FROM `ace-analytics.warehouse.fact_mot_test`
«hl:WHERE completed_date >= DATE_SUB(CURRENT_DATE(), INTERVAL 30 DAY)
  AND test_result = 'FAILED'»
```

Apply writes it to the tab; Reject discards it and tells the agent so it can try another approach.

A query arrives as a card with the dry-run estimate:

**chat → approval card**

<p>
      Dry-run: <b>1.2 GB · ~$0.006</b> · up to 100 rows
    </p>
    ```sql
SELECT make, COUNT(*) AS failed
FROM `ace-analytics.warehouse.fact_mot_test`
WHERE test_result = 'FAILED'
GROUP BY make ORDER BY failed DESC LIMIT 20
```

Estimate first, scan second. Reject sends the refusal back to the agent.

## Readonly

The agent can answer questions, explain, diagnose, and validate, but any call to change a tab is refused with a note that you'd need Approve or Auto. Queries still work, with the same **Run** card as Approve. It's a read-only mode for your tabs, not for BigQuery.

Use it when you want a second opinion on a query you don't intend to change, or when someone else's tab is open.

## Auto

Edits land in the tab and queries run as soon as the agent decides to. The agent's own guard rails still apply: it dry-runs SQL before executing, only `SELECT` is allowed, and every query respects the tab's [per-query limit](https://docs.querylab.io/writing-sql/cost-limits/) and your budgets. Every edit keeps one level of undo (**Revert** on the edit card), and the editor's own undo history is intact.

> **Auto still spends money.** A 20-step optimization can run a dozen queries. Keep a tight per-query limit   on the attached tab before you switch to Auto.

## Limits that apply in every mode

**25 tool calls per request.** Past that the panel shows **Iteration limit reached** with a **Continue** button; continuing counts as one more request against your quota.