A look inside the Propellus processing layer — how a visa application flows from a traveller's first message to a scored, validated, document-complete submission. Configured, not coded.
Propellus AI Engine processingEvery application is the runtime execution of a published workflow. The engine does four jobs.
Reads passport bio-page, photo, tickets, and supporting documents into structured, typed fields with per-field confidence.
Checks every field and image against destination requirements. Flags problems and auto-corrects within policy bounds.
Computes the Application Strength Score — approval likelihood with a per-dimension breakdown.
Runs the conversation turn by turn, branching on prior answers, routing to suppliers and payment.
The conversation a traveller has is built in a visual workflow builder — five node types, fourteen input widgets, bound to live platform data. Adding a destination or changing a government rule no longer takes an engineering deploy.
Propellus E-Visa AssistantThe assistant greets by agent brand, confirms residency and destination, and matches the right visa variant.
Collects traveller details, passport, photo, travel dates, and supporting documents through a chat — not a form.
AI reads each document and surfaces the fields for the traveller to confirm. Nothing is accepted silently.
Fields and photo are checked against destination rules; the assistant explains what it fixed or what still needs attention.
The Application Strength Score shows approval likelihood, a breakdown, and a ranked list of concrete fixes — before submission.
Payment is taken, the application is routed to the right fulfilment channel, and real-time status flows back to the traveller and the agency.
Before submission, the engine scores the application against historical destination outcomes and shows exactly how to improve it.
Application StrengthEvery AI surface across the platform follows the same principles.
Every output carries a High / Medium / Low indicator.
Every suggestion includes a one-line "why."
Accept, edit, or dismiss, every time.
Every suggestion and decision is logged.
One agency's data never trains another's.
No consequential action happens without explicit human confirmation.
Python monorepo with autonomous AI agents handling extraction, validation, scoring, and orchestration.
AWS and Azure with data residency options, built for government-grade compliance.
OCR-plus-structure models return typed fields with confidence, keyed to Document Hub schemas.
Every application generates a structured traveler record — identity, history, document quality, compliance signals. We're building the Travel Score: a real-time traveler identity graph sold to airlines, insurers, and governments as a data product.
Status: in design · targeted 2027Targeted availability: Q3 2026.