Your first Moona decision

You do not need an agent or a live database to see how Moona evaluates a command. moona try runs a command through Moona's full decision process and shows you the result — without executing anything.

Try a destructive command

This example shows Moona evaluating a command that would drop a production database table:

Moona evaluates the command — resolving the target host, identifying the SQL operation, checking it against your configuration — and prints the verdict:

Target: db.prod.example.com (production)
Operation: DROP TABLE users

✕ BLOCKED
Dropping a table on a production target is catastrophic and cannot be approved.

[nothing was executed]

What Moona evaluated

In this example, Moona:

1. Identified that db.prod.example.com is a production target (either declared in your configuration, or defaulting to production because it is a remote host).
2. Recognized the DROP TABLE operation as catastrophic on a production system.
3. Blocked the action outright. This is not a hold — it cannot be approved, even by you.

Try a lower-risk command

Not every command Moona evaluates is blocked. Try something that would be held for approval rather than refused outright:

A filtered delete — where rows are identified by a condition — is consequential but potentially legitimate. Moona would hold it pending your approval rather than blocking it outright.

What happens in normal use

Once your agent is guarded by Moona, this evaluation happens automatically for every command the agent issues. You do not need to manually invoke moona try in day-to-day use — it is a tool for understanding and testing Moona's behavior.

When Moona holds an action during a real agent session, the agent stops and waits. You resolve it with moona approve from your terminal, or from your phone if you have set up a notification channel.