Concept D · interactive · questions from the requisition and resume

The companion that reads along

The whole journey is here: sign in, Today with a two-week day strip, confirm the exact interview, then guidance or preparation. The companion listens to the call through the Evalzo bot. Suggested questions come from the requisition, the resume and any earlier round; the transcript runs alongside so you can ask for a follow-up on any answer. During the interview a one-line brief sits at the top and opens into a full view when wanted; Close returns to the questions untouched. Below it, three questions to start, and new cards only when the interviewer asks for them: tap a chip, Technical, Experience, Culture or Wrap-up, and it writes the request into the box for the interviewer to adjust and send. Three questions arrive grounded in that source, with a small Generate 3 more link under them. The transcript is behind a toggle, not in the way.

Chrome · Google Meet + Evalzo side panel

Signed out

Jump to step

Time now

What changed from concept A

Three at a time, on request

Concept A kept a single cue and a Next button. Here the panel opens with three questions and generates three more only when asked, so inference runs once per batch rather than on every utterance. Four prompt chips fill the box rather than firing: Technical from the requisition, resume and recent answers; Experience from the resume and the prior round; Culture from the criteria; Wrap-up from the plan. The interviewer can edit the request before sending. Generate 3 more sits under the batch it extends, inside the list.

The transcript runs inside the same list as the questions, with no tick, no asked detection and no match score: you read the question, you ask it, the answer arrives under it. Follow-up on anything Them says is the only thing that ties the two together. Each interview keeps its own timeline; the Switch control in the identity row moves between open sessions.

Steering, with a relevance check

Requests go through the same grounding as cards

In requisition and resume (Java, PostgreSQL): cards immediately, with sources.
In one of the two (AWS, React): cards with a caveat about what the other source says.
In neither (C++): the companion says so and asks before generating. Those cards are dashed and recorded as off-plan when ticked.

Limits to test

Not yet validated

Flags come from the written assessment record and resume-to-requisition comparison. Their wording needs a technical reviewer's sign-off so they read as prompts, not verdicts.
Listening is back, so the bot feed, participant notice and readiness checks return to the pilot scope. The transcript cannot identify speakers by name on the fly, only You (your audio) and Them (everyone else), so the timeline never labels a line with the candidate’s name. Asked detection and match scores were dropped to keep the call-time work simple.
Invitations follow the current Evalzo integration: a video interview is only confirmed once the calendar event is saved, and a written assessment is sent by Evalzo with its deadline. Neither claims acceptance.
Batch latency is simulated. Starting batches can still be generated before the call; follow-ups cannot.