Concept D · interactive · questions from the requisition and resume

The companion that reads along

The whole journey is here: sign in, Today, confirm the exact interview, then guidance. The companion does not listen to the call. Everything it suggests comes from the requisition, the candidate’s resume and any earlier round. During the interview a short brief sits at the top and expands only when wanted. 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

evalzo Companion

Signed out

Jump to step

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.

No live transcript. Dropping it removes the bot feed, the latency budget, the readiness checks and the notice step from the pilot, and the companion never processes what the candidate says.

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.
Without the transcript, follow-ups on what the candidate just said are the interviewer’s own. Test whether the Good answer line is enough support for a non-specialist.
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. Since nothing depends on the conversation, batches could be generated before the call starts.