Shabaz Badshah
Technical Product Manager
Currently: Shipping products independently for teams through Badshah Consulting. Building Syftable.
Owned and delivered to market a net-new patient pharmacy app in regulated Canadian healthcare (including Québec).
Launched a net-new digital pharmacy that patients loved (4.9/5, 350+ reviews)
Loved by patients: 400+ 5-star Google reviews.
Available across Canada: Localized in English and French.
PIPEDA & PHIPA adherence: Patient data/privacy, and operations compliant.
Integrations: PharmacyLink, StreamChat, Stripe payments, etc.
Vendor marketplace data consolidation API for reducing onboarding time using LLMs, REST/GraphQL, and Google Maps.
Onboarding per market cut from ~16 hours to 6 for operations team
My own product: a Mac app that follows your work as you do it, keeping track of the decisions, commitments and files you would otherwise have to remember. It processes and saves everything on your Mac, and acts only with your approval.
Some of my thoughts and things I'd like to share.
Featured, , 8 min read
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.
, 5 min read
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.
, 6 min read
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.
Syftable
