Aadil
Hassan

A heavy financial-data platform built entirely on AWS. It parses raw and scanned dealership financial statements into structured data, processes it to surface revenue-optimization opportunities, and lets non-technical stakeholders ask questions in plain English. I paired a fine-tuned LLM with a deterministic math engine so the numbers are always exact — no LLM arithmetic errors.

A data-heavy expert-sourcing system for a B2B expert network. I built the scraping and enrichment pipelines that pull and structure large volumes of medical-practitioner data, and surfaced it through interactive dashboards for client due-diligence and research — owned end to end, from the scraper to the visualization UI.

AI content, social publishing, email, SEO and rank-tracking, landing pages and a lead CRM — all driven by an AI chat command-center, with per-workspace cost metering and Stripe billing.

A free, open-source graphic-design tool — a Canva alternative with a full canvas engine, 1000+ fonts, stock photos, templates and watermark-free export, plus built-in GPT-4 and Claude for AI-assisted design. Its core editor kit is published on npm as @marketifyall/design-editor-kit.

A 7-layer email-deliverability pipeline — syntax, DNS/MX, disposable, role, typo-correction, catch-all and live SMTP checks — with batch and queue distribution and full unit-test coverage on every layer. Dual ESM/CJS build.

Connects Google Search Console to a Webflow CMS: finds underperforming pages, rewrites their metadata with Claude + LangGraph, deploys the change, then A/B tests it and auto-reverts if click-through doesn't improve.

Turns property listings into platform-optimized marketing videos: vision + script generation, viral-hook scoring, TTS, word-level caption alignment, automated FFmpeg rendering, and a quality-eval step that gates bad renders. Public REST API.

Real-time voice over Twilio Media Streams — Deepgram STT, ElevenLabs TTS, Groq-served LLMs — with barge-in for sub-second turns, Qdrant RAG knowledge bases, post-call LLM scoring as an eval loop, and a one-line embeddable widget.