STEP 01
WHAT WE INGEST
Read the brief
Cleo takes the brief, the must-haves, and the real constraints, then turns that into a search and interview plan.
→AI LABS · CLEO · INTERVIEW INTELLIGENCE
Find the right mind. Interview them on the spot.
Reads the brief. Returns a ranked shortlist with fit reasons. Runs outreach. Conducts the structured interview with live rubric scoring.
CLEO · LIVE INTERVIEW PROBE
BRIEF
Read once
Must-haves, constraints, and tone, in your words.
SHORTLIST
Ranked with reasons
Why each name surfaced. What they bring. What they don't.
VERDICT
Hire or no-hire
Structured interview. Live rubric. Transcript attached.
HOW IT WORKS
Three steps. One conversation.
Read the brief. Run the interview. Deliver a verdict the team can act on.
STEP 02
WHAT WE RUN
Shortlist + interview
Profiles are ranked by fit with reasons. Cleo runs outreach, then conducts the structured interview with live rubric scoring.
→STEP 03
WHAT WE SIGN
Deliver the verdict
Hire, no-hire, or human review. The transcript, the rubric, and the reason stay with the decision.
METHODOLOGY · FIVE STAGES
From the brief to the handoff, nothing leaves the record.
Five stages. One candidate record. Define the brief, match the shortlist, run the session, route the decision, hand the record off.
01 · DEFINE
Intake the brief
Cleo takes the brief, the must-haves, and the real constraints, then turns that into a search and interview plan. The plan stays attached to the candidate record from the first contact through the verdict.
Role brief · required skills · domain constraints → Search plan attached to the candidate record
02 · MATCH
Rank the shortlist with reasons
Profiles are ranked by fit, domain knowledge, and current availability so teams can see why each person surfaced. The reason chips travel with the shortlist into outreach.
Candidate profile · expertise tags · workload → Shortlist with fit rationale
03 · RUN
Live session with intent classification
The candidate meets Cleo in a structured session. Cleo asks, listens, captures transcript notes, and keeps the conversation moving. The intent strip on the side shows where the signal is moving.
Interview template · rubric · duration limits → Session transcript + intent strip
04 · ROUTE
Decide the next step with evidence
Cleo picks one of three paths: structured interview, direct assignment, or human review. The reason stays on the session. The recruiter sees what moved the call before they read the transcript.
Rubric score · availability · review signal → Routing decision with evidence
05 · HAND OFF
Structured round or assignment
Strong candidates move forward with a clear record. Ambiguous cases are escalated with the context a human reviewer needs. The handoff is the record, not a summary of the record.
Recommendation · normalized score · recruiter workflow → Clean handoff into the next surface
RANKING · EVERY RANK HAS A REASON
The ranking is configurable. No black box.
Ranking weights live in config. Teams review and sign off before the weights change. Every shortlist comes with the weights that produced it.
FACTOR 01
40%
Semantic similarity
How close the candidate's experience reads to the brief — not keywords, but meaning across role and domain.
FACTOR 02
25%
Experience score
Years of work, depth of programs, and the texture of the projects on file. Real work, weighted.
FACTOR 03
20%
Skill coverage
Coverage against the explicit skills the brief calls out, including adjacent ones the role tends to need.
FACTOR 04
10%
Availability
Whether they can start when the team needs them. Confirmed, not assumed.
FACTOR 05
5%
Referral signal
Internal references, prior calibration, and second-degree signal from the bench.
EXAMPLE SHORTLIST · ANONYMIZED
Candidate A.P.
96
Clinical NLP specialist
Oncology
HIPAA
NLP
AVAILABLE NOW
Candidate M.N.
93
Genomics data reviewer
Genomics
QA
Rubrics
2 WEEKS
Candidate L.A.
90
Safety & bias analyst
RLHF
Bias
Ethics
AVAILABLE NOW
Names anonymized. Example rubric. Teams configure weights per role before search runs.
ROUTING · THREE PATHS · ONE RECORD
Three routes out of every session. The evidence travels with each one.
Cleo does not pick a route in the dark. The rubric score, the availability check, and the review signals stay attached to the record the route was decided on.
PATH 01 · TO INTERVIEW
Route to a structured round
Signal is strong enough for a structured round. Cleo schedules the AI Interviewer session and attaches the rubric, the transcript, and the reason for the route.
SIGNALS
· Rubric fit above 0.80
· Availability confirmed
· No review flag
PATH 02 · TO ASSIGNMENT
Direct to calibrated work
Candidate is ready for calibrated work directly. Cleo hands them into Workforce with the trust-tier and the cleared rubrics attached.
SIGNALS
· Prior calibration on file
· Skill taxonomy match
· Workforce opening flagged
PATH 03 · TO HUMAN REVIEW
Escalate with the evidence
Edge case, review signal, or mixed rubric. Cleo pauses, keeps the evidence together, and brings in the recruiter on call.
SIGNALS
· Review flag triggered
· Rubric contradictions
· Novel role profile
RUBRIC · LIVE SCORECARD
The rubric moves as the session moves. So does the call.
Dimension-weighted rubric updates during the interview, not after cleanup work. The hiring team sees how a candidate is doing while the session is still running.
Notes stay on the row that earned them. The score doesn't arrive without the reason.
LIVE INTENT STRIP · SESSION ANN-8421
SCORECARD · IN PROGRESS
4.04 / 5 · WEIGHTED
Technical depth
4.2 / 5
WEIGHT · 35%
Strong on distributed systems; gaps in GPU optimization
Problem solving
3.8 / 5
WEIGHT · 25%
Clear reasoning; needed hints on edge cases
Communication
4.5 / 5
WEIGHT · 20%
Structured answers; good use of examples
Domain knowledge
3.5 / 5
WEIGHT · 20%
Solid NLP foundations; limited clinical exposure
PROGRAM NOTE · ON THE RECORD
“The first round used to eat half the team. Now Cleo runs it, the rubric stays the same across every candidate, and the recommendation is on the record before the candidate logs off.”
WHAT COMES OUT
What the brief turns into.
Every session leaves the record the team needs to defend the call — and the next interview can compare against.
01
Shortlists
A ranked list with the reason each name surfaced and what they don't bring.
↳ ARTIFACT
02
Rubric reads
Live scoring across the dimensions the brief calls for. The same rubric, every candidate.
↳ ARTIFACT
03
Interview transcripts
The full session, with the moments that moved the score marked and timestamped.
↳ ARTIFACT
04
Hire / no-hire verdicts
One read, with the rubric and the transcript attached. Routes ambiguous cases to a human.
↳ ARTIFACT
ADMIN GOVERNANCE
The session leaves with a policy check on it.
Before the candidate record hands off to Workforce or the ATS, the admin panel runs five checks. The state of each one stays attached to the session.
VOICE
Cleo · concise technical
The interview persona on file. Versioned, signed off, and attached to every session.
↳ ACTIVE
RECOVERY
Text-first interview handoff
When voice fails, the session continues in text without losing the rubric, the transcript, or the route.
↳ ARMED
AVATAR
Primary healthy · backup warm
The avatar provider posture, with the failover already prepared so the candidate sees the same Cleo.
↳ HEALTHY
WEBHOOK
Workforce + ATS sync
The handoff endpoints, with last delivery timestamps and the manifest hash that travels with each event.
↳ PASSING
ABUSE REVIEW
4 sessions paused
Sessions where the abuse classifier paused the conversation are surfaced for human review with the full transcript and the reason.
↳ REVIEW
QUESTIONS · BEFORE YOU RUN IT
What teams ask before they run Cleo.
Six questions, answered plainly. The same six come up on every program — recruiting, talent ops, and the program lead all want the same thing.
01 · ON THE RUBRIC
Whose rubric runs the interview?
Yours. Cleo runs the rubric your team has already been using. The rubric is versioned, the changes go through approval, and every session gets stamped with the version it was scored on.
02 · ON THE TRANSCRIPT
Where does the transcript live after the session?
On the candidate record, with the rubric, the routing decision, and the reason. The transcript is portable — it leaves the workspace as part of the handoff packet, not as a separate export.
03 · ON THE ROUTE
Can a human override Cleo's route?
Yes. The recruiter on call can override any route Cleo recommends. The override stays on the record with the reason and the rubric snapshot at the time it was made.
04 · ON THE PERSONA
Is the candidate told they are talking to AI?
Yes. The candidate sees the persona, the interview type, and the rubric structure before the session starts. The transparency is the policy, not a workaround.
05 · ON THE BACKUP
What happens when voice fails?
The session continues in text. The rubric does not reset. The transcript merges the voice portion and the text portion under one record, with the failover timestamp marked.
06 · ON THE HANDOFF
Where does a successful candidate go next?
Into Workforce, with the cleared rubrics, the transcript, and the route attached. The recruiter does not type a summary — the record is the summary.
WHAT CHANGES
What changes when Cleo runs the first round.
Specialist hiring breaks when search, outreach, and the first-round interview live in four different tools. The team keeps the brief in one place, the candidates in another, the notes in a third, and the rubric in a doc nobody touches. By the time a decision is needed, the evidence has already split.
Cleo collapses that into one workflow. The brief is read once. The shortlist comes with reasons. The interview runs live, scored as it happens. The recommendation is ready as the session ends, not after cleanup. And the record — every transcript, every rubric, every reason — stays with the candidate as they move into the next step.
WHERE IT FITS
In the loop, this is where you recruit.
Test the run. Review the hard cases. Recruit the right specialist. Remember the misses. Approve what's right.
01
Test
02
Review
03
Recruit
● YOU ARE HERE
04
Remember
05
Approve
RELATED MODULES
Next to this in the Human Data OS.
WORKFORCE
The right hands. The right work.
Specialists routed to the tasks they're best at. Their record follows them.
See the page →ANNOTATION
Where judgment becomes data.
Structured capture, with the reviewer's reasoning on the record.
See the page →EVALUATION STUDIO
Test it before it ships.
Codify the rubric, score every release against it, and ship with proof attached.
See the page →CLEO
Find the right mind. Interview them on the spot.
Bring the brief. Cleo brings the shortlist, the interview, and the verdict.