Skip to content
Apsan Works
Live2026

Olim Paveway

An AI planning tool that turns a fragmented, high-stakes immigration process into a personalised, document-backed plan.

The problem

Relocating to another country is a long sequence of interdependent decisions — eligibility, documentation, timing, finances, logistics — where the authoritative information is scattered across government pages, forums, and word of mouth. The information exists. What does not exist is a way to assemble it into a plan that reflects one specific person's situation, in an order they can actually act on.

What we built

  • 01

    A structured intake that captures the variables that genuinely change the path, rather than a generic questionnaire.

  • 02

    A generation layer that assembles a personalised plan from the intake, sequenced into actionable stages with the reasoning attached.

  • 03

    Server-side PDF generation so the plan leaves the app as a document people can print, share with family, and take to an appointment.

  • 04

    Transactional email delivery integrated into the flow, so the plan arrives without the user having to keep a browser tab alive.

  • 05

    A relational data model that persists plans, allowing them to be revisited and revised as circumstances change.

Decisions worth noting

Document as the deliverable

The product's real output is a PDF, not a screen. Designing for the artefact rather than the interface changed the data model, the generation flow, and what counts as done.

Structured generation

Plan content is generated into a defined schema rather than free prose, which is what makes it renderable, revisable, and consistent between runs.

Tell us what is slowing you down

A short conversation is usually enough to tell whether this is a build, an automation, or something you should not do at all. We will tell you which.