> ## Documentation Index
> Fetch the complete documentation index at: https://promptify.one/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Assistant console

> Talk to your assistant and debug responses with the latest model.

The **Assistant** page is a chat console bound to your configured assistant and model.

## How it works

When you send a message from this page, the app calls:

* `POST /api/assistant/message`

This endpoint:

1. Looks up your current assistant from Supabase.
2. Uses the assistant’s `instructions` as a system prompt.
3. Streams a reply from the selected model (base or fine‑tuned).
4. Stores the conversation in a `chats` + `messages` table pair for history.

The console reflects:

* **Model label** (e.g. `gpt-4o` vs a fine‑tuned model name)
* **Whether a fine‑tuned model is active** (depended on the last successful job)

## When to use it

Use the Assistant console to:

* Sanity‑check the assistant’s behavior before exposing the API
* Compare responses before and after fine‑tuning
* Reproduce problematic prompts so you can improve your specification