The six 100Networks AI recruiting agents

• Sourcing Agent — Finds the 35 people worth contacting. The Sourcing Agent turns your job description into a structured spec, runs a live search, and screens every profile against your criteria with the biased fields stripped out. Then it critiques its own coverage criterion by criterion and re-sources the gaps — up to five rounds — so you always get at least 35 ranked profiles, each with per-criterion evidence in full sentences.
• Outreach Agent — Email, LinkedIn and calls until they reply. The Outreach Agent picks a channel per candidate and escalates on its own — email, then LinkedIn, then an AI voice call — and holds a real conversation when they reply, inside a playbook you write. It respects working hours in their timezone, daily and weekly caps, a warm-up ramp, and a hard limit of one company per candidate every fourteen days, so your domain and your brand stay clean.
• Screening Agent — Ranks everyone on one bar, with the proof. The Screening Agent writes a scoring blueprint from your job description — no canned rubric — then scores every applicant across technical, core, behavioural and evidence pillars and sorts them into advance, review and reject at thresholds you set per job. It calibrates those thresholds against who you actually hired, and reports disparate impact both for its own raw calls and after your team’s overrides, so you can prove the bar was fair.
• Interview Agent — Interviews everyone. Coding, design, voice, take-home. The Interview Agent runs five kinds of round — AI voice screening, live coding with real execution, system design on a whiteboard, MCQ and theory, and take-homes — with seniority-aware questions generated from your job post and grounded in your own documents. It proctors throughout: camera, gaze, multi-face and lip-sync checks plus screen-share content detection, with a fifteen-second grace window and a screenshot on every violation.
• Notetaker — Joins your call. Leaves a filled scorecard. The Notetaker joins your Zoom, Meet, Teams or Webex round, transcribes it with speaker names, and scores each competency using your own interview template’s weighting — quoting the moment that earned the score. It pre-fills the scorecard as an AI draft your panel edits and submits, and produces a Minutes-of-Meeting PDF and an evaluation report on the way out.
• 100Networks Pilot — Runs the other five. Asks first. 100Networks Pilot is the conductor: you tell it what you want in plain English and it picks from 116 tools to do the work — over chat, WhatsApp or iMessage. Nothing it changes happens silently: every mutating action is staged as a proposal you confirm, with undo on supported actions for up to 24 hours, a company-wide kill switch and a full audit trail.