# Shabaz Badshah (Shabaz Badshah)

> Shabaz Badshah is a Product Engineer & Technical Product Consultant based in Ontario, Canada. He is a hybrid product manager and full-stack engineer building zero-to-one applications. He offers end-to-end software development skillsets, from system architecture to final market launch, implementing features end-to-end, from problem definition to design, development, testing, deployment, and post-launch support.

This site is the personal and consulting website of Shabaz Badshah. Content below is free to summarize and cite with attribution and a link to the source page.

## Pages

- [Home](https://shabazbadshah.com/): Introduction, about, contact links, selected work and blog posts

## Selected work

- [Mednow](https://shabazbadshah.com/#work): Shipped a B2C pharmacy app 0→1 to national launch.. A Canadian digital pharmacy app providing automated medication management and free nationwide delivery. It integrates holistic healthcare through virtual medical consultations, mental health support, and personalized wellness programs.
- [Upper Oakville Chiropractic](https://shabazbadshah.com/#work): Reduce monthly hosting costs by 90% and rebranded site. Established online presence to drive patient bookings by designing, building, and launching a clinic website end-to-end, including branding, WordPress development, post-launch support, PHIPA/PIPEDA/CCO compliance, and AEO/SEO.
- [Planned](https://shabazbadshah.com/#work): Reduced vendor onboarding time from 48h to 6h. REST API for consolidating disparate vendor data (Google Maps, PDFs, Yelp, etc.) using LLM technology to scale curated marketplace.
- [SOTI](https://shabazbadshah.com/#work): Grew revenue by $27K MRR CAD post-release. A custom instant-messaging and video calling tool (web and mobile apps) to communicate between MDM devices in order to provide technical support.
- [Project Include](https://shabazbadshah.com/#work): Ran 50+ workshops 250+ students prior to ending. An informational site volunteer nonprofit that empowers low socio-economic communities through free coding bootcamps and workshops.

## Blog

- [How LLMs actually work: An intuitive guide](https://shabazbadshah.com/blog/posts/how-llms-actually-work): LLMs work by predicting the next token, using embeddings to map meaning and attention to read context, then building a full answer one token at a time. Training on massive amounts of text, followed by fine-tuning for helpfulness, turns that simple loop into a capable assistant, which also explains why these models sometimes hallucinate. (2026-09-27)
- [How RAG (Retrieval-Augmented Generation) works](https://shabazbadshah.com/blog/posts/how-rag-works): RAG lets an AI answer questions about your own documents by finding the most relevant passages first and handing them to the model with the question. The model is the easy part; the quality of your chunking, search, and data freshness decides whether you get accurate answers or confident guesses. (2026-06-18)
- [AI and LLMs 101: A practical starter guide](https://shabazbadshah.com/blog/posts/ai-and-llms-101): This guide explains the core vocabulary of modern AI, including prompts, tokens, agents, MCP, skills, plugins, and Claude Code, in plain language. It ends with five practical steps to start using AI on real work today. (2026-04-12)
- [What Ontario clinics need to know about digital health rules in 2026](https://shabazbadshah.com/blog/posts/2026-ontario-healthcare-compliance-overview): Ontario clinics now face direct privacy fines, new oversight expectations for AI scribes, federal rules against vendors locking up patient data, and a push toward a shared provincial health record. To stay compliant, clinics should check their audit logs, AI review processes, data export capabilities, staff access controls, and where their patient data is stored. (2026-02-03)
- [The end of the handoff: Why product and engineering need to merge](https://shabazbadshah.com/blog/posts/the-end-of-the-handover-model): AI has made building software cheap, so the real bottleneck is now knowing what to build, and the old handoff between product managers and engineers wastes time, loses intent, and creates technical debt. Product-engineering fusion, modeled on the forward deployed engineer, puts business judgment and technical execution in one owner, producing simpler, compliant, and more usable systems faster than a traditional siloed agency. (2025-08-23)

## Contact

- [/in/shabaz-badshah](https://www.linkedin.com/in/shabaz-badshah/): Connect
- [@ShabazBadshah](https://github.com/ShabazBadshah): Follow
- [badshah.shabaz@gmail.com](mailto:badshah.shabaz@gmail.com): Email
- [Video call](https://calendly.com/badshah-shabaz/30min): Video call

## Optional

- [Full content for LLMs](https://shabazbadshah.com/llms-full.txt): Complete text of every blog post and project
- [Sitemap](https://shabazbadshah.com/sitemap.xml): All indexable URLs