Login

Hints

How a hint appears

When the other side asks something, a short hint appears, written the way you would say it out loud, and fills in as the AI writes. A few self-hosted AI endpoints answer all at once instead. Under the hint are the one to three things they are really asking about, and code gets a box of its own with a Copy button.

A hint filling in as the AI writes
  1. A hint still being written: its text fills in as the AI writes it
Hints in the chat
  1. The phrase the hint answers; click it to jump there
  2. The hint, written to be said out loud
  3. The one to three things they are really asking about

Several hints at once

A new question is answered at once, beside the hints still being written, up to three at a time. Past that, questions wait and are answered together.

Help me

Ctrl+Alt+S, or , takes a screenshot of the screen you chose and asks for help with it and the last minute of the call, in one press. The window itself is never in the picture.

Help me: the screenshot sent with the hint that answers it
  1. Your screenshot, in the chat with the words "Help me with what is on my screen"
  2. The hint that answers it

Capture

Ctrl+Alt+P, or , takes the same screenshot but only adds it to your next question, so you can collect several screens (up to 10) and send them together with a typed question.

A captured screenshot sent with a typed question
  1. The screenshot you captured, sent with the question you typed

Ask by typing

Type a question in the input bar (the window tour shows it) and press Enter, or Ctrl+Alt+A to send without focusing the window.

Documents and images

Paste an image (Ctrl+V), drop files on the window, or choose them with . Documents can be .txt, .md, .pdf, .docx, or .doc where LibreOffice is installed, up to 20 MB each and up to 10 per question; they are read on your computer, and only their text goes with your question. A PDF that is only a scan has no text to read.

The input, with attachments
  1. What waits for your next question
  2. A document attached to your question
  3. Every queued file has on its corner (tooltip "Remove this document" or "Remove this image") that takes it off
  4. An image: click it to see it at full size
An image at full size
  1. closes the picture and goes back to the chat

A second language

With a language you pick as the Call language, a Quick-switch language row shows in Settings, then Language. Ctrl+Alt+K then switches speech recognition and the hints to it, and the next press switches back; the switch lasts until you quit. The row's note names the key, and Change the key there opens Shortcuts. On a stream to our hosted service the switch takes effect in place, from the audio already sent on, so the phrase under way is kept and nothing is sent or charged twice. Under Automatic the row is hidden, and the shortcut changes nothing: it says the language is detected automatically, and that to switch it by hand you pick a language in Settings, then Language.

Your profiles

Keep a profile for each kind of call, with a few lines about you and your role, so the hints draw on your real experience. Switch the profile in the header, even mid-call. On a plan with credits, every hint uses credits; see what a credit buys.

Settings, then Profiles lists your profiles, one per row, as the picture shows (the app starts with one, Default). The language the hints are written in is the Call language, in Settings, then Language; English is the default, see Languages.

The Profiles settings
  1. The round button at the start of a row (tooltip "The model answers with the active profile") makes that profile the active one, the one the header's picker also switches
  2. The profile's title; the app starts with one profile, Default
  3. (tooltip "Edit") opens the profile in the editor below the list, Edit profile
  4. (tooltip "Delete") deletes the profile; the last profile cannot be deleted
  5. The wide button under the rows, (tooltip "New profile"), adds a profile and opens it

An open profile shows under Edit profile with three fields, saved with Save like any other setting:

The editor of a profile
  1. Title: its name in the header's picker; required, unique among your profiles, at most 60 characters
  2. About me: who you are, in a few lines. Hints bring in your experience only when a question is about you or asks for an example from your work; it is sent to the model with every question, so keep it a summary: at most 4,000 characters
  3. System instructions: the rules the model follows when it writes a hint; required
  • Title: its name in the header's picker; unique, at most 60 characters.
  • About me: who you are, in a few lines: your role and years, your stack, notable projects and what they achieved. Hints bring in your experience only when a question is about you or asks for an example from your work. It is sent to the model with every question, so keep it a summary: at most 4,000 characters. The button Fill from a document… (tooltip "Draft About me (and, if you like, the System instructions) from a CV or notes, for you to review") drafts it from a CV or notes, and you review the draft before it goes in.
  • System instructions: the rules the model follows when it writes a hint. The default ones ask for short answers you can say out loud, code only when someone asks for it, and silence for small talk. Change them only for a call that needs other rules.