Gig Worker Onboarding

Gig Worker Onboarding

Call stalled gig applicants in their own language, walk them through KYC + first-shift activation, and text a one-tap document link — turning drop-offs into active earners.

Built on the Telenow App Platform as a pure declarative app: the data model, the agent tools, the ATS webhook, the activation workflow, the vernacular agent, and the onboarding knowledge base all run on-platform. No external server.

The problem (and the number)

Gig and logistics onboarding leaks badly at the bottom of the funnel. Roughly 40% of applicants drop off somewhere between applying and their first shift — stuck on a blurry document, an OTP that didn't arrive, or a rumour that "joining costs money." It is a vernacular, mobile-first audience: about 68% of Tier-3 job seekers are mobile-only, so a form nudge or an English email does nothing. And the volume is enormous — India's logistics sector alone onboarded ~2.1 million workers in 2025. Every applicant who stalls is a slot the operations team already paid to acquire, sitting one phone call away from earning.

The single highest-leverage fix is a fast, human, vernacular call: reach the applicant while intent is warm, name the exact step they're stuck on, bust the myth that stalled them, and get them to their first shift.

Gig Worker Onboarding does exactly that, automatically, in the applicant's own language.

How it works

Your ATS  ──(stalled-applicant webhook)──►  onboarding object (status: active)
     │                                                  │
     │                                        fires object.onboarding.created
     ▼                                                  ▼
  dedupe on phone                          ┌── activate_stalled workflow
                                           │     ├─ delay ~3 min
                                           │     └─ outbound-call  {{settings.activation_agent_id}}
                                           │           → dials {{trigger.data.phone}}
                                           │           → passes worker_name, stage, language,
                                           │             reporting_location, stalled_hours
                                           │                 │
                                           │                 ▼
                                           │   Activation Agent (Sarvam, vernacular)
                                           │   find_worker → guide docs/KYC (KB)
                                           │   → advance_stage → record_availability
                                           │   → mark_activated | mark_dropped
                                           │
                                           └── send_doc_link workflow
                                                 └─ send-message  {{settings.wa_channel}}
                                                       → one-tap {{settings.doc_link_base}} upload link

Everything the agent does on the call updates the same onboarding rows you see on the dashboard — and the dashboard's Call now button dials through the same agent and tools.

Agent tools (used mid-call — all declarative)

The bundled Activation Agent is a multi-context flow: a deterministic find_worker tool node (looks the applicant up in this app's data) → a conversation node that guides the exact stuck step, advances the stage, captures availability, and activates. STT/TTS default to Sarvam (anushka) for vernacular, mobile-only Tier-2/3 applicants.

Dashboard pages

• Gig Worker Onboarding (dashboard) — KPI tiles (stalled in queue, drop-off recovered, activation rate, dropped, total), an onboarding funnel (share of applicants who reached at least each stage), the stalled queue sorted most-stuck-first, and a status mix. Also powers the platform dashboard_widget slot in a compact form.
• Workers — the stalled queue filtered by stage (applied / doc upload / KYC / first shift) or by status (activated / dropped), search, and Call now to trigger an activation call for any stalled applicant (passes their context variables to the agent).
• Setup — a configuration checklist, a one-click Create activation agent button, and the post-install wiring steps.

Knowledge base

onboarding-kb ships four real scripts the agent answers from: documents needed to complete onboarding, KYC steps and how verification works, first-shift reporting instructions, and common FAQ / myths that cause drop-off (joining is free, no deposit, documents are safe).

Install & post-install wiring

1. Install Gig Worker Onboarding into your org.
2. Open Setup → Create activation agent (builds the bundled Sarvam agent, auto-wired to the tools + KB).
3. Copy the new agent's ID into the app's Activation agent ID setting (activation_agent_id) so activate_stalled can dial.
4. (Optional but recommended) Set WhatsApp channel ID (wa_channel) and Document upload link base URL (doc_link_base) so send_doc_link texts the one-tap upload link.
5. Point your ATS's stalled applicant webhook at the inbound hook ats_stalled (HMAC-verified via x-ats-signature, dedupes on phone). Stalled applicants now flow in and auto-dial.

Settings

Bulk dialing your backlog

The real-time path (webhook → workflow → call) covers newly stalled applicants. To sweep an existing backlog, use the app-key campaign API:

POST /api/app-campaigns
{ "agentId": "<activation agent id>",
  "targetQuery": { "status": "active", "stalled_hours": { "$gte": 24 } },   // over the `onboarding` object
  "result": { ... write-back ... } }

Monetization

Gig Worker Onboarding is billed on outcomes, not seats:

• Per activated worker — a success fee for each applicant the agent brings all the way to activated (KYC done, reporting location captured, first shift committed). Each one is a hire the operations team would otherwise have lost, so the fee is a fraction of the re-acquisition cost.

Recovered drop-offs and the closing gap between "Applied" and "Activated" on the funnel make the ROI obvious on the dashboard.

Changelog

1.1.0 — 2026-07-12

• Renamed to Gig Worker Onboarding (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: onboarding object (worker name, phone, stage, language, reporting location, stalled hours, status, created_at) with stalled_queue / kyc_pending / activated / dropped saved views.
• Agent tools (declarative): find_worker, record_availability, advance_stage, mark_activated, mark_dropped.
• Bundled agent: Activation Agent — a Sarvam vernacular multi-context flow (deterministic find_worker lookup → guide the stuck document/KYC step, advance the stage, capture availability + reporting location, activate or drop) auto-wired to the tools and the onboarding knowledge base.
• Knowledge base: onboarding-kb — documents needed, KYC steps and verification, first-shift reporting instructions, and the common FAQ/myths that cause drop-off.
• Automation: ats_stalled inbound webhook (HMAC-verified via x-ats-signature, dedupe on phone); activate_stalled workflow (delay ~3 min → outbound activation call); send_doc_link workflow (WhatsApp the one-tap document-upload link).
• Dashboard UI: KPI tiles (stalled in queue, drop-off recovered, activation rate, dropped, total), an onboarding funnel, the most-stalled queue, and a status mix; also renders into the dashboard_widget slot in compact form.
• Workers page: stage + status filters, search, and per-applicant Call now (passes onboarding context variables to the agent).
• Setup page: configuration checklist + one-click Create activation agent and post-install wiring steps (agent ID → settings, ATS webhook, campaign API).
• Self-seed: a fresh install auto-loads six realistic demo applicants spread across every stage and status (removable) so the dashboard is populated on first open.