Skip to content
Currently available — for the right work·France891-Day French Streak·2026 Q1 calendar opens 06 Jan
↩ Projects · 2026 · 2026
Capstone · Submitted · Creator · Dhaka

VisaPros

Submitted as the capstone for the Google × Kaggle 5-Day AI Agents Intensive (2026). VisaPros is an agentic visa eligibility advisor — parses your documents once, then runs six parallel country agents (UK · Canada · US · Australia · Norway · Germany) as FastAPI microservices to evaluate your fit across every major destination simultaneously. A strategic advisor synthesises the results into a ranked migration roadmap with prioritised document gaps.

Role
CreatorSolo build
Period
2026 →shipping
Stack
PythonFastAPI · Gemini 2.5 Flash Lite · A2A Hub-and-Spoke
Location
DhakaOSS, MIT licensed
UKCAAUUSNODEVisaPros
01 · The problem

The Context

Anyone considering migration faces the same wall: dozens of countries, dozens of visa categories, dozens of evolving rule sets, and zero way to compare your actual eligibility side-by-side. Generic chatbots hallucinate immigration law; consultants charge for what should be a 20-minute parallel evaluation.

VisaPros treats each destination as a sovereign expert. You upload your documents once; six country specialists read them in parallel and report back what you qualify for, what's missing, and which route is the highest-yield next step.

02 · What I built

What I built

  • Agent-to-Agent (A2A) hub-and-spoke architecture. A central orchestrator parses documents sequentially (accuracy-critical), then fans the structured profile out to six country agents that evaluate independently as FastAPI microservices.
  • Six destination specialists. UK · Canada · US · Australia · Norway · Germany — each agent knows its own visa categories (tourism, business, study, healthcare, work) and applies them against the parsed profile.
  • Real-time grounding via Google Search. Country agents validate against current immigration rules at evaluation time, not stale training data — critical because immigration policy drifts monthly.
  • Strategic advisor synthesis layer. Ranks countries by eligibility yield, flags the "low-hanging fruit" path, and recommends the smallest set of additional documents that unlock the most options.
  • Structured JSON document extraction. Passport, education certificates, work history, financials — all normalised into a profile schema the country agents consume identically.
03 · What I learned

What I learned

The first architecture was a single linear agent that walked all six countries serially. It was correct, slow, and brittle — one country's edge case stalled the whole pipeline.

Splitting into parallel country microservices was the unlock. Accuracy lives in the sequential parser; speed and resilience live in the parallel agents; judgement lives in the strategic advisor. Three separate concerns, three separate components — exactly the boundaries a multi-agent system is supposed to have.

04 · Capstone context

Capstone context

Built and submitted as the capstone project for the Google × Kaggle 5-Day AI Agents Intensive (2026) — a programme focused on production-grade agentic systems: multi-agent orchestration, grounding, evaluation, and tool use.

VisaPros is the artefact: a complete A2A microservice mesh, real-time grounding, and a synthesis advisor — shipped solo, end-to-end, under MIT.

Engineering Deep Dive

High-calibre architecture decisions.

Technical Highlights

  • Agent-to-Agent (A2A) hub-and-spoke orchestration across six country specialists.
  • Gemini 2.5 Flash Lite for low-latency parallel inference across all destinations.
  • FastAPI microservices — each country agent independently deployable and scalable.
  • Google Search grounding for real-time immigration rule validation.
  • Sequential document parsing → parallel evaluation → strategic synthesis (three-stage hybrid pipeline).

Key Decisions & Rationale

Sequential parsing, parallel evaluation, synthesised advice

Document extraction is accuracy-critical and must stay deterministic; country evaluation is independent and parallelisable; final recommendation needs cross-country judgement. Three distinct workloads, three distinct components.

A2A microservices over a monolithic agent

A single linear agent stalled on one country's edge case. Splitting into six independent FastAPI services means each country can fail, retry, or update its rules without blocking the others.

Google Search grounding at evaluation time

Immigration policy drifts monthly. Baking rule data into the model weights guarantees stale answers. Live grounding keeps every evaluation current — and forces the agent to cite its source.

Performance Metrics

By the numbers.

Google × Kaggle
Capstone (Submitted)
6
Country agents in parallel
Any
Visa type — tourism, study, work, healthcare
05 · Interface & Sound

Visual & Audio Synthesis Showcase

Experience the alternate voice chemistry and responsive design. Stream pre-synthesized audio drops generated dynamically.

VisaPros — Google × Kaggle 5-Day AI Agents Intensive capstone submission. "An ecosystem of AI solution to Visa Eligibility for Embassies and Individuals." Six destinations evaluated in parallel.
VisaPros — Google × Kaggle 5-Day AI Agents Intensive capstone submission. "An ecosystem of AI solution to Visa Eligibility for Embassies and Individuals." Six destinations evaluated in parallel.
Collaborate

If we worked together.

I bring high-leverage product engineering and absolute operational discipline: shipping weekly, pressure-testing user inputs, and automating delivery pipelines.

Next case study

Global Jute Trading

Editorial export site for Global Jute Trading Ltd — a Dhaka-based sourcing & exporting house with 26 years as a company and 35 years of jute trading under its principals. Built to support their push into deeper international markets, with a particular focus on Canada.