AuraOne
Start a project

Internal demo · Cleo recruiting surface

Cleo, in preview.

A read-only walkthrough of the shipped Cleo surfaces — avatar session, intake, intent classification, routing decision, admin editor, and robotics jobs board. Every count on this page reads from the platform’s live metrics feed.

Open the Cleo product pageSign in to run Cleo live
active sessions
0
completed sessions
0
abuse-flag queue
0

Avatar session · read-only

The session surface, seeded and frozen.

This is the same layout your recruiters open in production. The live version streams transcript and rubric updates — this preview shows a seeded session so the visual shell survives audits without needing a real candidate on camera.

Live · read-onlycse_8A4L2
00:12:47

Cleo

Avatar · speaking

Audio stream Candidate mic live

Transcript

  • 00:11:12Cleo: Walk me through how you would design a rubric for hallucination detection in clinical summaries.
  • 00:11:41Candidate: I would start with a three-axis rubric: factual grounding, omission severity, and clinical actionability.
  • 00:12:18Cleo: Good framing. How would you weight omission severity against factual grounding?

Session

Candidate N.K.

Clinical NLP Specialist

INTERVIEWINGabuse-flag: clear

Intent classification

  • Interview intent92%
  • Domain knowledge84%
  • Reasoning quality78%

Shortlist · ranked

  • 1Candidate N.K.94Now
  • 2Candidate M.P.88Now
  • 3Candidate R.S.822 weeks

Candidate intake

From brief to handoff in one pass.

Four steps. Each one stays on the same candidate record, so the final recommendation inherits everything that happened earlier.

  1. 01

    Role brief

    Recruiter drops the brief, must-haves, and domain constraints so the session starts with intent.

  2. 02

    Candidate arrives

    Cleo greets the candidate by avatar, captures consent, and confirms the brief in plain language.

  3. 03

    Structured exchange

    Rubric questions run with intent classification live — the recruiter watches the session without intervening.

  4. 04

    Clean handoff

    Transcript, rubric score, and recommendation attach to the candidate record. No inbox round-trips.

Intent classification

Four signals, updated live.

The intent strip runs in the platform during live sessions. This preview shows a representative slice so teams can see the signals before they commit to the real run.

  • Interview intent92%
  • Domain knowledge84%
  • Reasoning quality78%
  • Communication88%

Routing decision

Three paths. One record.

After the session, Cleo chooses one path. The evidence and the reason for the choice stay on the session so reviewers can retrace it.

Route to interview

Signal is strong enough for a structured round. Cleo schedules the interview and attaches the rubric.

  • Rubric fit above 0.80
  • Availability confirmed
  • No abuse flag

Route to assignment

Candidate is ready for calibrated work directly. Cleo hands them into Workforce with the trust-tier attached.

  • Prior calibration on file
  • Skill taxonomy match
  • Workforce opening flagged

Escalate to a human recruiter

Edge case, abuse signal, or mixed rubric. Cleo pauses, logs the evidence, and pages the recruiter on call.

  • Abuse-flag triggered
  • Rubric contradictions
  • Novel role profile

Admin surface · HTML reproduction

Persona, fallback, review, integrations — one panel.

The shipped admin page gives recruiting leads one place to govern the avatar. This reproduction mirrors the layout; the real editor lives behind the platform sign-in.

Cleo · Admin/recruiting/cleo/admin
version 2026.04 · draft

Persona editor

Voice, tone, and interview-style versions with diff + rollback on every change.

Fallback script

Manual override script for when the avatar provider blips — candidate keeps a coherent session.

Abuse review queue

Flagged sessions with intent evidence, admin decisioning, and ledger-backed audit trail.

Provider + webhooks

Avatar provider selection, webhook destinations, and integration health at a glance.

No screenshot exists at docs/evidence/ux/<date>/hiring-workforce/cleo-admin.png; this HTML reproduction stands in until Phase 5 captures one.

Robotics jobs board · mini

Three seeded openings — the shipped format.

Bounty, pay, and required kit stay attached to each job. Cleo can route an assignment-ready candidate directly into one of these postings.

  • rbt-104

    Bimanual package-sort demonstration

    Pay rate
    $42/hour
    Required kit
    UR5 + depth camera
    Bounty multiplier
    1.4×
  • rbt-113

    Warehouse picking · edge cases

    Pay rate
    $38/hour
    Required kit
    Franka Emika + stereo rig
    Bounty multiplier
    1.2×
  • rbt-127

    Assembly-line handoff trajectories

    Pay rate
    $48/hour
    Required kit
    Operator rig · dual-arm
    Bounty multiplier
    1.6×

Capability strip · tier-scoped

What ships at each tier.

Per the anonymization policy, this page does not publish revenue or named-customer numbers. Here is the product-tier capability strip instead.

  • Starter

    Cleo avatar session, intake flow, rubric library, and AI Interviewer review — billed per completed session.

  • Scale

    Adds robotics jobs board, auto-recruit routing, webhook integrations, and admin persona versioning.

  • Enterprise

    Adds per-tenant persona governance, abuse-flag escalation SLAs, and deployment-scoped audit export.

Next path

The production surface is one sign-in away.

Open the Cleo product page for the full story, or sign in to run a real session with your own brief and rubric.

Open the Cleo product pageSee the Workforce demo
Cleo demo · read-only preview · live-metrics JSON bound000