Drop-off is spread across the entire funnel — application, assessment, scheduling, interview, and offer. The cost is real, recent, and measurable.
Coldness is computed from time-in-stage. Each signal below triggers a tailored, compliant re-engagement.
A 5-minute sweep reads time-in-stage across the whole funnel and flags candidates going cold — computed, since the ATS emits no "cold" event.
A pre-approved WhatsApp template re-opens the conversation. The candidate’s reply opens a 24-hour window for free-form, adaptive chat.
Winston, the AI assistant, runs a warm, personalized, multi-turn conversation — collecting answers or booking time via in-chat WhatsApp Flows.
It logs the outcome back to the ATS and alerts the recruiter. It never advances or rejects — every stage move stays human.
A high-level functional walkthrough for executives — the prototype workflow, the public-domain resources it was grounded in, and the cloud infrastructure it runs on (with zero Sutherland data).
Under the Hood →