Skip to main content
Alpha. Your Exterview team enables it for your workspace. In the Alpha, a role run contacts a job’s candidates, raises a review card to your Agent Inbox, and shows its progress in the Control plane. You can pause, resume or stop it. Starting a run yourself, sourcing, outreach replies and the later report moments are Upcoming. Available to everyone today: screen-to-rank (EX Call, EX Voice and EX Avatar through scoring to the Leaderboard), AI Employees in chat, Smaya ask and report chat, and the MCP server. See What is Available today.

Purpose

An agent swarm is how Smaya will run hiring for a role. You give it the role. It builds the pipeline, talks to every candidate, gathers the evidence, and brings you the people worth deciding on. You see outcomes and reports. You do not manage agents. The work between reports runs in the background, and you step in when there is something to decide.

What a swarm is

A swarm is one run per role, plus one sub-run per candidate. Each run is built from pre-built agents in the Agent Library. Each sub-run carries one candidate from first contact to a decision-ready report.

One instruction

You start a role with the role, your notes and, if you have them, example profiles. That is the last thing you are asked until a report exists.

Many candidates at once

Every candidate moves through the same steps at the same time, on the same criteria. Candidate one and candidate fifty stay comparable.

Reports, not tasks

You will never approve an email or a slot request. You answer reports and accept schedules, and nothing else.

How a role runs, end to end

Solid lines work today. Steps marked Alpha work where your workspace has the Alpha. Dotted lines are Upcoming.
1

Run the role (Upcoming)

You give the role in one instruction, from Exterview or from a connected assistant. The scoring criteria are locked for the run, so every candidate is assessed the same way. Today, criteria are already locked per job when you create it.
2

The run contacts candidates (Alpha)

A run splits the job’s candidates against its résumé bar. Those at or above it get an invite email, a WhatsApp message and an AI phone screen, by policy. Everyone else waits on one review card, where you choose who to include. Hired, rejected and withdrawn candidates are never contacted.
3

Candidates move through the pipeline

Today, each candidate is screened with EX Call, EX Voice or EX Avatar, scored against the locked criteria and ranked on the Leaderboard. Upcoming: finding and researching candidates as steps of the run.
4

Reports reach your Agent Inbox

Alpha: a review card. Upcoming: reports at key moments in each candidate’s journey, and a schedule when the run needs a person’s time.
5

You answer

Proceed, Drop or Talk on a report. Accept, Decline or Talk on a schedule. Each answer is recorded with who gave it and why. Alpha: answering the review card, where a No asks for your reason and is recorded as a Drop. Without the Alpha, you review reports in the Decision Center and change a decision with a stated reason.

Reports at key moments

As designed, each candidate’s journey produces reports at key moments, each with the evidence behind it. Steps that involve a hiring decision or your team’s time always wait for a person. In the Alpha, a run raises a review card. The underlying phone screen and AI interview reports are Available today in the Decision Center. See Agent Inbox.

What runs on its own

As designed, the swarm works between reports without asking you anything.

Finding and researching

Upcoming. Sourcing candidates for the role and building a picture of each one: experience, fit and the best way to reach them.

Reaching out

Alpha. Contacting candidates by email, WhatsApp and an AI phone screen. Upcoming: reading their replies.

Screening and interviewing

Available. Phone screens with EX Call, AI interviews with EX Voice or EX Avatar, each producing a report.

Scoring and ranking

Available. Scoring against the locked criteria and keeping the Leaderboard current as interviews complete.
Today you trigger each screen and interview yourself, or ask an AI Employee to. In the Alpha, a run places the phone screen for each candidate it contacts. Setup decisions — the scoring criteria, the interview design, the agent’s role for the job — happen before the run starts. They are never Inbox items.

Human oversight that does not move

Autonomy between reports will never move a hiring decision to a machine. These rules hold today and apply to every run.

People make hiring decisions

No automated step sets a candidate to hired, rejected or withdrawn. The swarm recommends. A person decides.

Drop is a human decision on record

A Drop moves the candidate out of the queue with who decided and why. It never marks the candidate rejected.

Notice before every AI interview

A candidate confirms they have been told AI is part of the interview before every AI interview starts. No automated step can skip it.

Nobody is hidden

Candidates below the bar stay visible for a person to review. Nothing suppresses a result.
As designed, every decision that moves a candidate in a run is recorded with who made it: a person, a time-window policy, or the candidate. See Governance & Control.

What is Available today

Further automation across the hiring journey is Upcoming. See Upcoming.

FAQs

In part, as an Alpha that your Exterview team enables for your workspace. A run contacts a job’s candidates and raises a review card. Sourcing, replies and later reports are Upcoming. Without the Alpha, you screen, interview, score and rank candidates yourself or with an AI Employee, and decide in the Decision Center.
No. You will give the role and answer reports. Which agents do the work is the platform’s job.
No. Only a person can set a hiring outcome. A Drop in the Agent Inbox is your decision, recorded with your reason, and it never marks the candidate rejected.
In the Alpha, a run contacts candidates at or above the job’s résumé bar on its own. Everyone else waits for you on a review card. You set the criteria and the agent’s role for the job before the run starts.
No. Criteria are locked for the run. A change applies to the next run.