Jignesh Sanghani · Full-Stack Engineer · Team Lead
I build SaaS and AI products, and lead the team that ships them.
Eight years at AppStoneLab, building web, SaaS and AI products for startups, agencies and growing businesses. I lead the team, own the technical architecture, and work directly with the people the product is for.
01 · What I do
What I do.
Six things the job is made of, from the screen down to the database and out to the team that ships it.
Product Engineering
The whole slice of a feature: the screen, the API behind it, the schema under that, and the migration that gets there. Most of my work looks like this: SaaS platforms, eCommerce, content and knowledge-base systems.
02 · Writing
Latest from the blog.
Practical notes, guides and lessons from building and operating real products.
·25 min read8 Types of Specialized AI Models Every Developer Should KnowThe types of AI models beyond chat: LLM, VLM, SLM, MoE, LAM, MLM, SAM and both LCMs, how each one works, and when a developer should reach for it.AI
·8 min readRAG Examples: Same Pipeline, Different RetrievalReal RAG examples, from web search to support bots, share one pipeline and differ only in retrieval. A hybrid Postgres setup to start from, with code.AI
·7 min readWhat Vector Embeddings Are, and Where They HelpWhat vector embeddings are, the four product problems they solve, where a plain index still wins, and why pgvector beats a vector database first.AI
·10 min readCut a 300s Product Filter Query to 30s With a Lookup TableA correlated EXISTS join across a 12M-row product/category pivot took 300s. Denormalizing the filter columns into one indexed lookup table dropped it to 30s.PerformanceSay hello.
Questions about anything here, or about the work. I read everything that arrives.