ORACLE HCM · AI AGENT PROFILE

Interview agents

Two agents that help with interviews. The Interview Insights Generator analyses interview transcripts from Interview Companion, writes an interview summary, and pre-fills interviewers' feedback questionnaires, including ratings, as drafts for them to review. The Recruiting Interview Resources Agent writes interview guidelines when an interview or interview schedule is created and the field is empty.
RecruitingAI agent (two agents: Interview Insights Generator and Recruiting Interview Resources Agent)Good first agent: NoHigherChanges dataRelease 26C

Where it helps

After a Teams interview, the interviewer gets a notification, opens feedback already drafted from the transcript, corrects two answers and submits it.

My take

MY PRACTITIONER VIEW

Feedback drafted from a transcript is a real time-saver, but a pre-filled rating is a strong nudge. Make sure interviewers review and change the draft, not just accept it.

Things you can ask

After an interview, interviewers receive draft feedback to review and edit.
When you create an interview with empty guidelines, they're written for you.

Examples based on Oracle's notes. What works depends on your setup.

What it won't do

  • The insights agent only works for web-conference interviews set up through the Zoom or Microsoft Teams integration, completed with Interview Companion, with a feedback questionnaire.
  • It doesn't pre-fill rating-only feedback without a questionnaire.
  • It drafts feedback; it doesn't submit it.
  • Guidelines are only written into empty fields, and not for shared interview schedules or templates.
  • Three candidate-facing fields are only filled if someone clicks AI Assist.

Good first agent?

No. It drafts feedback and ratings about candidates.

Risk level: Higher. It drafts feedback and ratings about candidates, which feed hiring decisions.

Before you switch it on

  1. Have candidates been told interviews are transcribed and analysed by AI?
  2. Will interviewers review every draft, and can you tell whether they changed anything?
  3. Who checks that summaries reflect what was actually said?

Next steps

Setup at a glance

Open Setup at a glance for the setup steps. Select the agent's type label to see what that type means.

Test it after each update

For Oracle Fusion Applications, non-production (test) quarterly updates follow the weekend after the first Friday of the update month; production follows the weekend after the third Friday. Run these checks after the test update and before production, and verify your tenant's exact dates in Oracle update notifications.

  • Run a test interview and check the summary against the transcript.
  • Check the draft feedback reaches the interviewer to review and isn't submitted automatically.
  • Create an interview with empty guidelines and check what's written.

Watch out

Interviewers may accept a pre-filled rating without thinking. Consider tracking how often drafts are changed.

How it's changed

26C interview summaries, draft feedback and interview guidelines; 26D interview loops and topic tracking in Zoom interviews; 26D topics and suggested questions tracked live in Zoom interviews (Interview Companion)

  1. 26D
    Track Topics and Questions During Zoom InterviewsOracle's note ↗
  2. 26C
    Redwood Experience: Create Interview Summary and Populate Questionnaires Using AI AgentOracle's note ↗
  3. 26C
    Redwood Experience: Generate Interview Resources Using AI AgentOracle's note ↗

Related agents

Last reviewed November 2026

This is an independent practitioner view, not Oracle documentation. Features, names and availability change each release and depend on your licences and setup; some agentic applications carry extra costs. Always check Oracle's own notes and your environment.