How AMI actually works

The whole pipeline, where each part runs, and what it cannot do. If you are going to rely on this during an interview, you should know how it behaves.

The pipeline Staying hidden The answers Where your data goes What it cannot do

The pipeline, step by step

Four stages. Two happen entirely on your computer.

  1. Capturing the conversation

    AMI captures your system audio output — what the interviewer's voice is coming out of — plus your microphone. It does not join the call, install a bot, or appear as a participant. As far as the meeting software is concerned, nothing extra is there.

    Runs on your computer
  2. Turning speech into text

    A speech-recognition model ships inside the app and runs on your own CPU. It buffers speech, waits for a natural pause, then transcribes that chunk and decides whether it looked like a question worth answering.

    Runs on your computer — the audio is never uploaded
  3. Writing the answer

    The question text, along with the background you gave AMI and your chosen tone, is sent to our server. The server holds the AI credentials — that is why you never need an API key — and streams an answer back token by token.

    Runs on our server — question text only
  4. Putting it on screen

    The answer appears on a compact overlay that is excluded from screen capture, kept out of the taskbar, and kept out of alt-tab. It streams in as it is written, so you can start speaking before it finishes.

    Runs on your computer

Staying hidden

What AMI does

  • Excluded from screen capture. The overlay window asks Windows to leave it out of anything that captures the screen, which is how screen sharing works.
  • Not in the taskbar. No icon to notice.
  • Not in alt-tab. It will not surface when windows are cycled.
  • Always on top, quietly. It stays readable above the meeting window without stealing focus or clicks.

Verify it yourself

Do not take our word for it. AMI includes a check that captures your screen exactly the way a screen-share does, then tells you whether the overlay appeared in the captured image.

  1. Start an interview session so the overlay is open.
  2. Go to SettingsTest my invisibility.
  3. Press Run invisibility check.

Run it on the machine you will actually interview on, before the interview. Results can vary with your graphics driver and Windows version, which is precisely why the check exists.

What this does not protect against. Software screen capture is one route in. It cannot help against a phone or camera pointed at your screen, a hardware capture device between your PC and monitor, someone sitting next to you, or proctoring tools that inspect running processes rather than the picture. Treat it as hiding a window from a screen share, not as invisibility.

The answers

Written for you, not generic

  • Your background. You tell AMI about yourself once, and answers are written in the first person from that.
  • Real context. Because it follows the whole conversation, an answer can build on what was already said instead of restarting.
  • Your tone. Formal or conversational, concise or detailed — switchable per session.
  • Points, not a script. Answers come as a few specific points you can speak from, rather than a paragraph to read aloud, which sounds like reading aloud.

Speed and models

  • Streaming. Text appears as it is generated, so you can begin talking after the first point.
  • Trial model. The free trial uses a smaller, faster model.
  • Paid model. Every paid plan uses a 70B-class model — better on unusual questions and at holding context.
There is one paid plan, so there is no better or worse answer quality to buy into — the model difference is free versus paid and nothing else. See plans in detail.

Where your data goes

Split by what leaves your computer and what does not.

ItemLeaves your computer?Notes
Interview audioNoTranscribed locally by a model bundled in the app
Question textYesSent so an answer can be generated
Your background / profileYesSent with the question so the answer is about you
Display name & languageYesStored with your device record
Trial time usedYesCounted server-side so it is consistent
Email addressYesOnly if you create an account
Card detailsNoHandled entirely by Paddle; they never reach us

Read the privacy policy

What it cannot do

Stated up front, so nothing here is a surprise during an interview.

It needs an internet connection

Transcription is local, but answers are generated on our servers. With no connection, AMI listens and transcribes and cannot reply. There is no offline answer mode today.

Windows only

Windows 10 and 11, 64-bit. No macOS, no Linux, no web version. The screen-capture exclusion it depends on is a Windows feature, so a port is not a recompile.

It is not a lie detector, and it does not know the company

Answers are built from the background you provide and the conversation. AMI does not research the employer, and it can be confidently wrong about facts. Read what it suggests before you say it.

Audio capture depends on your setup

AMI captures your system output and your microphone. Unusual routing — virtual audio devices, some headsets, per-application volume set to silent — can mean one side is not picked up. Test a session before it matters.

Whether you are allowed to use it is on you

Many employers and assessment platforms prohibit assistance. AMI does not check the rules of your interview, and it cannot. That call, and its consequences, are yours.

Try it free for 40 minutes See plans