Assistant

Ask about your apps in plain words: why a deploy failed, why an app is slow, what changed, what to do next.

The assistant is in beta. It only works once the platform has been set up for it; until then it answers "not set up yet" (see assistant_unavailable).

Open Assistant in the dashboard, or run deplane ask "QUESTION". On a failed build, Ask the assistant why opens it with the question filled in.

What it can see

The assistant looks things up the way the dashboard does, as you, in your team only: your apps and their status, recent app and build logs, releases, metrics, alerts, custom domains, workers and cron jobs, databases, your variables' names, and the GitHub connection. It never sees your variables' values.

What it can do

It explains, and when a change would help it shows a Confirm button. Nothing changes until you click it. The change runs with your permissions, with the same passkey check as anywhere else, and the card shows exactly what will happen (for example the repository, the command, or the variable names). In the CLI it prints the command instead.

It can suggest:

• scaling an app or a worker, turning on autoscaling or sleep when idle (Scaling), rolling back, redeploying, and deploying the latest commit;
• adding, re-checking, or removing a custom domain;
• creating an app from a GitHub repository the Deplane GitHub App can see, optionally with a database;
• creating a database and attaching it to an app, or detaching one (the database is kept);
• restoring a database into a new one at a moment in its backup window, and switching apps to it (the original database is never changed);
• adding a worker or cron job;
• setting or removing variables. It proposes the names; you type the values into the card, so the assistant never sees them.

It cannot delete apps or databases. Use the Delete button on the app's Settings tab or the Databases page.

Where your data goes

Answers come from Claude, made by Anthropic. To answer, Deplane sends Claude your question and the data it looks up for it (for example log lines and metrics). Anthropic does not use API data to train its models. Text inside your apps' logs is treated as data, never as instructions to the assistant.

Answers can be wrong: check them before you act. You can ask 40 questions an hour.

This page is also available as Markdown. AI agents can start at /llms.txt.