Instant Candidate Screening

Instant Candidate Screening

Screen every job applicant with a structured voice call within 60 seconds of applying — capture typed answers, auto-score fit, and hand recruiters a ranked shortlist.

Built on the Telenow App Platform as a pure declarative app: the data model, the agent tools, the applicant webhooks, the screening workflow, the vernacular agent, and the screening-playbook knowledge base all run on-platform. No external server.

The problem (and the number)

Recruiter screening is where hiring quietly bleeds time and money. Manually calling, qualifying, and note-taking eats roughly 23 recruiter-hours per hire, and each phone screen costs $32–58 in loaded recruiter time. Meanwhile speed is everything: fewer than 1% of organisations reach an applicant within 5 minutes — and for high-volume, hourly, and blue-collar roles the best candidates are gone in hours, often already screened by whoever called first.

Instant Candidate Screening closes that gap. The moment an application lands, it calls the candidate, runs a consistent structured screen in their own language, records every typed answer, scores fit against the role, and drops a ranked shortlist on the recruiter's desk — before a human has read the first résumé.

How it works

Meta Lead Ads / ATS  ──(applicant webhook)──►  candidate object (status: new)
        │                                              │
        │                                   fires object.candidate.created
        ▼                                              ▼
   dedupe on phone            ┌──────────────────────────────────────────────┐
                              │ notify_new_candidate → WhatsApp heads-up      │
                              │ screen_new_candidate → delay ~30s →           │
                              │   outbound-call {{settings.screen_agent_id}}  │
                              │     → dials {{trigger.data.phone}}            │
                              │     → passes name, role, source, location     │
                              └──────────────────────────────────────────────┘
                                              │
                                              ▼
                        Instant Screening Agent (Sarvam, vernacular)
                        find_candidate → structured Q&A → record_answer
                        → set_fit → shortlist | reject

Every answer the agent captures and every status it sets updates the same candidate rows you see on the dashboard — ranked by fit — and the dashboard's Call now button re-screens any applicant through the same agent and tools.

Agent tools (used mid-call — all declarative)

The bundled Instant Screening Agent is a multi-context flow: a deterministic find_candidate tool node (looks the caller up in this app's data) → a conversation node that runs the ordered question list, scores fit, and sets status. STT/TTS default to Sarvam (anushka) so Tier-2/3 and vernacular applicants are screened in Hindi, Tamil, Telugu, Kannada, Marathi, or English.

Dashboard pages

• Instant Candidate Screening (dashboard) — KPI tiles (applied today, screened, shortlisted, average fit score), the applied → screened → shortlisted funnel with drop-off, top candidates by fit, and a status mix. Also powers the platform dashboard_widget slot in a compact form.
• Candidates — the ranked shortlist: status filter chips, search, a colour-coded fit pill against your cutoff, the captured screen answers inline, and per-row Call now (passes the candidate's context variables to the agent) plus quick shortlist/reject.
• Requisitions — open roles with openings, location, status, and shortlisted-vs-openings fill progress.
• Setup — a configuration checklist, a one-click Create screening agent button, and the post-install wiring steps.

Knowledge base

screening-playbook ships four real docs the agent screens from: the structured question list (asked in order), role requirements (per-role must-haves), instant disqualifiers (hard stops), and the 0–100 fit scoring rubric.

Install & post-install wiring

1. Install Instant Candidate Screening into your org.
2. Open Setup → Create screening agent (builds the bundled Sarvam agent, auto-wired to the tools + KB).
3. Copy the new agent's ID into the app's Screening agent ID setting (screen_agent_id) so screen_new_candidate can dial.
4. (Optional) Set Minimum fit score (min_fit_score, default 60) to move the shortlist bar, and WhatsApp channel ID (wa_channel) to auto-send applicants a screening heads-up.
5. Point your applicant source at the inbound hook — meta_leads (token-authenticated URL, for Meta Lead Ads via a normalizer) or ats_webhook (HMAC-verified with the signature header, for Greenhouse / Lever / Workable). New applicants now flow in, dedupe on phone, and auto-dial within ~60 seconds.

Settings

Bulk-screen your pipeline

The real-time path (webhook → workflow → call) covers new applicants. To screen an existing pipeline in one sweep, use the app-key campaign API:

POST /api/app-campaigns
{ "agentId": "<screen agent id>",
  "targetQuery": { "status": "new" },      // over the `candidate` object
  "result": { ... write-back ... } }

Point targetQuery at any saved view (to_screen, screening) to re-screen a segment.

Monetization

Instant Candidate Screening is billed on outcomes, not seats: per qualified screen — a small fee each time the agent completes a structured screen and returns a scored candidate (a shortlisted or rejected decision with a saved fit_score). You only pay when a real applicant is actually screened and ranked, which maps directly to the recruiter hours and per-screen cost it removes. Suspected duplicates and unreachable numbers are not billed.

Changelog

1.1.0 — 2026-07-12

• Renamed to Instant Candidate Screening (business-friendly) with a marketplace icon.
• Added real UI screenshots (dashboard + key pages).
• Verified end-to-end loop closure: trigger → workflow → call → agent tools → write-back → dashboard.

1.0.0

• Initial release.
• Data model: candidate object (name, phone, role, source, availability, expected_salary, location, shift, languages, two_wheeler, fit_score, status, created_at) with to_screen / shortlist / screening saved views, plus a requisition object (title, role, openings, location, status) with an open_reqs view.
• Agent tools (declarative): find_candidate, log_candidate, record_answer, set_fit, shortlist, reject.
• Bundled agent: Instant Screening Agent — a Sarvam vernacular multi-context flow (deterministic find_candidate lookup → structured screen capturing availability/salary/location/shift/languages/two-wheeler → score → shortlist/reject) auto-wired to the tools and the screening playbook.
• Knowledge base: screening-playbook — structured question list (in order), per-role requirements, instant disqualifiers, and the 0–100 fit scoring rubric.
• Automation: meta_leads (Meta Lead Ads) + ats_webhook (Greenhouse/Lever/Workable, HMAC-verified) inbound hooks that dedupe on phone; screen_new_candidate workflow (delay ~30s → outbound screening call within 60s of applying); notify_new_candidate workflow (WhatsApp the applicant a heads-up).
• Dashboard UI: KPI tiles (applied/screened/shortlisted, average fit), the applied → screened → shortlisted funnel with drop-off, top candidates by fit, and a status mix; also renders into the dashboard_widget slot in compact form.
• Candidates page: fit-ranked shortlist, status filter chips, search, colour-coded fit pills against the cutoff, inline screen answers, and per-row Call now (passes candidate context variables to the agent) plus quick shortlist/reject.
• Requisitions page: open roles with openings, location, status, and shortlisted-vs-openings fill progress.
• Setup page: configuration checklist + one-click Create screening agent and post-install wiring steps.
• Self-seed: a fresh install auto-loads six realistic demo candidates across every status and three requisitions (removable) so the dashboard is populated on first open.