AI assistant
An opt-in, grounded chat sidebar over the database you're connected to.
RED has an AI assistant in a sidebar - toggle it with ⌘L. It's grounded in the database you're connected to: rather than guessing, it reads your schema (and, when you allow it, runs read-only queries) to answer questions, explain an error, or draft a query.
Opt-in and off by default
The assistant makes no network calls until you turn it on and configure a provider. RED itself has no telemetry - the assistant only talks to the provider you choose.
Connecting a provider
Point the assistant at Claude one of two ways, from Settings → Agents:
- Claude API - paste an API key.
- Claude subscription - sign in with your existing Claude plan (a browser-based, paste-the-code flow). Settings shows who's signed in and lets you sign out or switch accounts.
How it stays grounded
The assistant is read-only and works through a small set of database tools, gated by an access tier you control - globally in Settings, or per connection:
| Tier | What the assistant can do |
|---|---|
off | Chat only - no database access at all. |
schema | See structure: tables, columns, types, and keys - never a row of data. |
read | The full read catalog: schema plus SELECT and EXPLAIN. The shipped default. |
Even at read, a connection's read-only posture is honored and queries run under
resource guards (row caps, timeouts). It never writes.
Working with it
- Ask in plain language - "why is this query slow?", "what references
orders?", "give me the last 10 signups". - Explain an error or optimize a query with one click from the relevant chip.
- A footer tracks tokens and cost for the turn.
- Conversations are saved - reopen, rename, or delete past chats, and keep several going at once (each bound to its own provider).