Your first conversation

Open a project, type a question, press Enter. That's the whole ceremony. This page is about reading what comes back.

What a turn looks like#

A turn is one thing you said plus everything the agent did before you spoke again. Turns are separated by generous space, and they render in this order:

Your message, in a raised bubble. Any attachments sit above your text as chips.

A left gutter with one dot per step, if the agent did anything besides talk. Amber means a tool is running, green means it finished, red means it failed, and a hollow ring is a thinking step. A turn that's pure conversation gets no gutter at all — the answer just flows.

The agent's thinking, collapsed behind a single word. Click it to read.

Tool cards for each thing the agent did — see What the agent can do.

The answer, as plain markdown. No bubble, no avatar, no name label; the agent's prose is simply the text of the page. Code blocks are syntax-highlighted with the language named in the corner.

While the answer is still empty, nothing is drawn — the indicator above the message box is your only sign that work is happening.

Scrolling, and the thing that makes it feel right#

When you send a message, the view moves so your message sits at the top of the screen and the answer streams into the space below it. History glides up rather than snapping.

The transcript follows the bottom of the stream as it grows — until you scroll up. Then it stops following and stays where you put it. New output never yanks the view out from under you.

Four things start it following again: scrolling back to the bottom yourself, clicking the ↓ button that appears when you've scrolled away, sending another message, or switching to a different conversation and back.

Finding your way around a long conversation#

The rail on the right edge is one tick per turn — faint until you move the mouse near it. Hover a tick to see that message's text; click to jump to it.

The sticky bar at the top shows the message for the turn you're currently reading, once its bubble has scrolled out of view. Click it to jump back to the real thing. Show more expands it if the message was long.

Things you can do to a message#

Hover any message of yours and a small toolbar appears at its bottom-right.

Copy puts your message text on the clipboard.

Replay folds the conversation back to that turn and opens a stepper — see Conversations and history.

Restore rolls your files back to how they were before that message. Click once to arm it, again to confirm; it posts a notice saying how many files changed. The messages stay — only the workspace moves. A checkpoint of the current state is taken first, so the restore itself can be undone.

Clone copies the conversation up to that point into a new chat, so you can take a different path without losing this one. It's offered on the most recent turn.

Remove deletes that turn — your message and the response — permanently. Click twice within three seconds.

Reading a tool card#

Tool cards carry the filename the agent was working on. Click the filename and the file opens in a tab, at the relevant line when the tool had one. It's the fastest way to check the agent's work as it goes.

Diffs are shown inline up to about fourteen lines; show more opens the full diff in a window that closes with Escape.

The size of the text#

Settings → General → Chat has a font size stepper with a reset link. It scales the whole conversation. It's separate from the editor's font size and from Ctrl/Cmd +/−, which zoom the rest of the interface.

What the agent is told that you don't see#

Two things ride along invisibly. On the first message of a conversation, Semantix attaches a compact map of your project — a file list, two levels deep, capped at 300 entries — so the agent starts with a sense of the shape of things instead of spending its first tool calls discovering it. It's never sent again.

Every message also carries the current time.

Neither appears in your bubble, and neither is counted as something you typed.