Live Interview Copilot

1. The app captures your computer's audio. Whatever the meeting is playing through your speakers or headset is captured at the system level. There is nothing to route, no virtual audio device to install, and you do not need to add the app to the call.
2. That audio is transcribed as it arrives. The interviewer's words appear in the panel while they are still speaking.
3. The question appears in the ANSWERING box. This is your check that the copilot understood. Filler such as "okay, great, so" is removed; click the box to see the words Exactly as heard:. If it heard the wrong thing, fix it with Ask rather than reading out an answer to a question nobody asked.
4. The answer is generated from that transcript. It streams into the panel underneath, written in the first person so you can read it out. It uses your resume, the job description, your instructions and, from 5.0, your About you answers, prepared answers and memory of previous interviews.

From 5.3, answers use plain, everyday words and short sentences, so they are easy to say out loud. When the question is about the difference between two things (for example, git pull and git fetch), the answer gives each side its own short paragraph and says when to use which.

1. 1

   Step 1: Check Interview Setup says Ready

   Open ⋮ → Interview Setup. The header pill must read Ready to start an interview, which means a resume is uploaded and Interview category and Specific domain are chosen. Paste this role's job description while you are there, pick the answer length and tone you want to read out, and fill in About you if you have not yet. The Interview Setup guide explains every field.

   

   Shared computer?

   Interview Setup is saved to the signed-in account. If someone else used this machine with your account, check the resume and About you before you start; the AI answers as whoever's resume is loaded.
2. 2

   Step 2: Join the meeting as usual

   Open Zoom, Meet or Teams (desktop client or browser, either works) and join the call on your normal speakers or headphones. The app captures the meeting audio from your computer, so there is nothing to route.
3. 3

   Step 3: Choose your domain if asked

   There is no mode to pick: one session handles spoken questions and screen captures. (In 4.0.16 and earlier, pick Live interview on the mode chip first.) If you have not chosen a domain yet, pressing Start opens an Interview Domain Selection dialog (Choose your interview domain to get specialized AI assistance tailored to your field) with categories such as Software Development, Cloud Computing & Infrastructure, Data Science & AI, Business & Management and Healthcare & Sciences. Pick the closest match and click Start Live Interview. Your choice is saved and shown under ⋮ → Interview Setup → This interview, so later sessions start immediately.
4. 4

   Step 4: Upload your resume if asked

   Sessions need a resume so answers reflect your real experience. If none is on file, a Resume Upload dialog appears (Upload Your Resume (Required); PDF, DOC, DOCX or TXT up to 10 MB). Text is extracted on your computer. Uploading a new resume later, from this dialog or from ⋮ → Interview Setup, replaces the old one completely and the next answer uses the new one.
5. 5

   Step 5: Click Start and confirm the details

   A Confirm interview details screen appears first, listing the domain, your name and target role, resume, job description, instructions, your preferred coding language if you set one, interview language and how answers are triggered. On the right, Based on your previous interview sessions shows what the copilot remembers from earlier rounds, with a switch to leave it out of this interview. Check it all matches, then click Details are correct — start interview (or Edit details to fix something). Nothing is billed until you confirm; the confirm screen guide explains the option to skip it for a profile you always use. Once confirmed, billing starts. The Start button becomes a red End, a timer and a speaker icon appear in the toolbar, and a Hide button lets you collapse the answer panel. The transcript panel shows what the interviewer says as they say it. Nothing appears on the shared screen.

   

   • Transcription runs on the meeting audio your computer plays. Keep the call on your normal speakers or headphones; if you mute the meeting, nothing is transcribed.
   • Transcription goes live about a second after you confirm, so the interviewer's first words are not missed.
   • Ctrl/⌘ + Shift + U pauses and resumes listening if you need a moment off the record.
6. 6

   Step 6: Get an answer after each question

   Let the interviewer finish, then press Ctrl/⌘ + Enter (or click Answer; Ctrl/⌘ + Space and, with the LastRound AI window in front, Space do the same). The copilot reads the latest transcript, shows the question in the ANSWERING box so you can confirm it understood, then streams the answer underneath. The next section covers exactly when it will and will not answer.
7. 7

   Step 7: End the session

   Click End (or press Ctrl/⌘ + Shift + E). Billing stops at that moment. After an interview with at least two spoken questions you get your interview recap about ten seconds later. Your questions and answers are saved to Live Interview → Interview History in the web app unless you chose Keep on this device only under Settings → Account → Privacy & Local Data.

1. 8

   Step 8: Click Ask, or press Ctrl/⌘ + Shift + I

   The pill expands into a text field with the placeholder Type your question... and the overlay widens to make room for it. Nothing else changes: the session keeps running, the transcript keeps filling, and no credit is spent by opening the field.
2. 9

   Step 9: Type the question or the instruction

   Write it the way you would say it. It does not have to be a question: rewrite that answer in twenty seconds, give me the trade-offs instead and what would you ask me next all work.
3. 10

   Step 10: Press Enter

   Or click the arrow button beside the field. The answer streams into the same panel as any other answer. Esc clears the field and collapses it, the ✕ closes it, and clicking away collapses it too as long as it is empty.

   Open Ask from the keyboard: Ctrl/⌘ + Shift + I

   From desktop 5.4.1, Ctrl/⌘ + Shift + I opens the Ask box from any app, so you do not have to click it. Enter or Ctrl/⌘ + Enter sends, Esc closes. The overlay comes to the front so the box can take your typing. On 5.4.0 and older Ask has no shortcut: your mouse pointer is visible to the other side of a screen share even though the overlay is not, so move deliberately rather than hunting for the button mid-sentence.

A long interview is one conversation, not forty unrelated questions. The five most recent exchanges are replayed to the model word for word, and everything before them is folded into a short note of what has already been discussed, so an answer in minute 40 stays consistent with what you said in minute 5. If you named a tool, a project or a number early on, a later answer will not contradict it, and when the interviewer refers back ("you mentioned earlier that...") the answer builds on what was already said. The note is built in the background while the answer streams, so it costs you nothing in speed, and it is cleared when you end the session.

Separately, from 5.0 the app keeps a short memory of your previous interviews so the next round stays consistent. You can see, edit, switch off or clear it in Interview Setup.

• Copy copies the whole recap as text, for your notes. Practise these in a mock interview opens a mock interview in the web app.
• The recap appears after an interview with at least two spoken questions. It does not appear after the demo interview.
• Do not want it? Click Don't show after interviews, or switch off Recap after each interview under ⋮ → Interview Setup → How the AI answers. The same switch turns it back on.

Theme changes apply straight away. The other settings apply when you click Save Settings, and like Interview Setup they are saved to your account.

1. 11

   Step 11: Capture the screen

   Press Ctrl/⌘ + H (or click Capture). The app captures the display your mouse pointer is on, so with two monitors move the pointer onto the screen that shows the question first. Each capture goes into the queue and the badge on Capture counts it; nothing is sent yet. Ctrl/⌘ + L removes the last one and Ctrl/⌘ + R clears the queue. Capture the whole question, including examples and constraints: for a problem that spans more than one screen, scroll and capture each part.
2. 12

   Step 12: Press Answer

   Press Ctrl/⌘ + Enter (or click Answer). The new screenshots are sent as one question, and the panel shows Reading the screen and working it out while the AI reads them. A screen answer takes a few seconds, up to 20 for a hard problem, because the AI checks its work before it writes; a spoken question still gets its fast answer in a second or two. If no session is running yet, clicking Capture or pressing Answer starts one (after the confirm screen).

   Coding and test platforms vary

   Follow each platform's rules. If a test forbids outside help, or uses proctoring software you have to install (a lockdown browser or proctoring app), don't use LastRound AI for it. From 5.3 the app shows a warning when it sees proctoring software running.
3. 13

   Step 13: Not right? Use the buttons under the answer

   Every screen answer and every answer with code has Regenerate, Another approach and Explain simpler on the Answer line (keys Ctrl/⌘ + Shift + G, Y and X). They are covered below.

• Click the mode chip and pick Coding round (Code / assessment before 4.0.15), or press Ctrl/⌘ + 2, then Start. The Coding Interview Setup dialog asks for a Round Type and a Programming Language, prefilled from ⋮ → Interview Setup → Coding rounds. Click Start Coding Interview.
• Capture the problem with Ctrl/⌘ + H and press Ctrl/⌘ + Enter. Code is written in the language you chose. Online tests with multiple choice or short questions work in Live interview mode and do not need a Coding round.
• Billing works exactly as it does in Live mode.

1. 14

   Step 14: Start fixes the length of the session

   When you press Start, the app converts your balance into minutes and sets a deadline for the session there and then. Fifteen credits buys a fifteen-minute session. The ceiling is 480 minutes, which is 8 hours, whatever your balance. If your balance is below 1 you never get this far: there is no Start button, only Subscribe. Reaching Start another way (a keyboard shortcut, for instance) gives you Insufficient Credits and You need at least 1 credit to start a session. Current balance: 0.
2. 15

   Step 15: Buying credits mid-session does not extend it

   The deadline set at Start can be shortened, if the same account spends credits somewhere else while you are running, but it is never lengthened. Credits bought during the interview apply to your next session, not to this one. If you need more time, you have to end the session and start a new one.
3. 16

   Step 16: At the deadline the session ends itself

   You get a short message reading Credit limit reached and This interview ended automatically at your available credit limit. The session is already over by the time you have read it; there is no confirmation step and no way to extend it. Transcription stops, the timer stops, and the toolbar goes back to its pre-session state.

   There is no warning in the last minute

   The app does not count you down to the end of a session. Running low on credits, with a line reading "N credits left — top up to keep going without interruption", is tied to your account balance rather than to the session clock, so in practice you see it before you start rather than during. Treat the balance you had at Start as the whole story.
4. 17

   Step 17: If the balance itself reaches zero, the same thing happens

   Spend the account's credits elsewhere while this session runs and you get Out of credits with Your session paused — top up to start again. The session ends about a second later. Despite the word "paused", it is not resumable: you start a new one.
5. 18

   Step 18: Answers stop before the session does

   If the balance is already at zero, pressing Answer gives you No Credits and You have no credits remaining. Please top up to continue., and the Ask button is greyed out with the note No credits remaining — please top up. That is your last warning before the session closes.

What to do about it

When the transcription connection drops, the app reconnects it immediately, and retries twice more with a short pause between attempts. If none of those take, it switches to the other speech provider automatically. The whole sequence takes about a second. You do not restart the app, you do not restart the session, and audio capture is never torn down, so the meeting audio keeps flowing throughout and the interviewer notices nothing.

A reconnect to the same provider is silent. A switch to the other one shows a brief Transcription Restored notice naming the provider that was unavailable. In the rare case that both are unreachable you get Transcription Error, which asks you to end and restart the interview; that is the only case where you have to do anything.

If the connection goes quiet while the interviewer is speaking, the app notices within a few seconds and reconnects by itself, without waiting for a timeout. The words spoken during a short drop are kept and appear a few seconds late instead of being lost. There is no need to restart.

From 5.5.2 the amber banner reads Heads-up: followed by the app's name and is running on this computer. If your test runs inside it, it may detect overlay apps. Browser tests like LeetCode, HackerRank or CodeSignal are fine. If your test runs inside that app, take it without LastRound AI. If you are practising or interviewing in a normal browser tab, carry on. 5.5.2 also stops background helpers (for example an exam browser's updater service) from raising the banner when the exam app itself is closed.

The keyboard shortcuts reference has the full list, including moving and resizing the overlay, and the combinations that take precedence over other apps while LastRound AI is running.

1. 22

   Step 22: Open Mobile Copilot on your phone

   Sign in at app.lastroundai.com on your phone and choose Live Interview → Mobile Copilot. Complete Resume and Experience, then tap Start Interview.

   Open Mobile Copilot
2. 23

   Step 23: Follow the Ready to Start checklist

   • Allow Microphone when the browser asks.
   • Position Device where it can hear the interviewer clearly.
   • Generate Answers: tap Generate Response after each question.
   • Mute When Speaking so your own voice is not transcribed.
3. 24

   Step 24: During the interview

   Tap Start Session. The status line shows Listening.... After a question, tap Generate Response; use Mute / Unmute while you answer, and End when you are done. Bluetooth headsets are not recommended: the phone should hear the room directly.

1. 25

   Step 25: Review past sessions

   In the web app open Live Interview → Interview History. Each entry shows the date, session type (every 5.0 session is LIVE, screen questions included; CODING appears only for older sessions), domain, duration and number of questions. Expand an entry to read the questions and answers, download it, or delete it. The desktop app opens it from Settings → Help → Interview history, already signed in.

   

   Prefer not to keep transcripts?

   Turn off Interview review history under Settings → Data & privacy in the web app, or choose Keep on this device only under Interview history in the desktop app's Settings → Account → Privacy & Local Data. Duration and credits are still recorded for billing.