PlacementFlow screens every candidate in two stages — the Qualifier (a quick first chat: the universal basics plus your must-knows) and the Screening (a deeper AI screen with scored questions) — with your personal review in between, on every channel. Nothing is rejected automatically at either stage — mismatches are flagged, and every decline is yours.
Before any deep screening happens, the candidate answers the Qualifier — the universal PlacementFlow basics (location, right to work, notice, work setup, salary expectations, ideal next role) plus your own must-knows. It's asked first on every channel: WhatsApp, web chat, and the SMS-linked web form.
Must-knows are fact checks, not automatic gates:
Candidates are never told they failed. Whatever they answer, the conversation closes on a neutral "our recruiter will review your answers."
After the Qualifier, everything stops. On every channel — WhatsApp, web, SMS — the candidate's answers land at Needs Review → Qualifier, and you personally decide whether they continue, based on what they actually said, not just their sourced profile data.
When you approve, PlacementFlow sends the candidate a personal invitation from your own connected mailbox — your name, your agency, referencing their answers — with the Screening link (plus a text nudge when a number is on file). The link stays live for 7 days, with at most two gentle reminders. WhatsApp candidates simply continue in the same chat.
Candidates you approve move into the full conversational screen:
The AI then scores the response 0–100 and attaches a recommendation.
| Score | Recommendation |
|---|---|
| 70 or above | Advance — strong fit, no critical concerns |
| 50–69 | Review — worth a look, has open questions |
| Below 50 | Reject — critical mismatches |
These are recommendations, not silent decisions. Every scored response appears in your review queue at Candidates → Screening, and you make the call. Optional auto-advance exists for high scores — but it never fires on a response flagged "Didn't meet must-knows". Flags always get human eyes.
If the AI can't produce a valid score (an outage, a timeout), you'll see an amber scoring unavailable warning on the response instead of a number. PlacementFlow never fabricates a score — the candidate's raw answers stay available, you can read them and decide manually, or hit Retry AI Scoring. A background job also retries failed scorings automatically.
A friendly chat — on WhatsApp or the web — that takes a few minutes, asks one question at a time, and is upfront about being an AI assistant with human recruiters reviewing every conversation. It always ends the same way: a neutral close, with the decision in your hands.