Engineering notes from the Urnish Tech team
Production patterns, infra deep dives, and what we have learned shipping software at scale.
AI
Generative AI explained in plain words: LLMs, RAG, embeddings, knowledge graphs, evals and AI agents, with real examples and a working reference build.
GenAI Quick Answers and Series Guide
Short, plain answers to the GenAI questions we hear most: hallucination, RAG vs fine-tuning, cosine similarity, HNSW, HyDE, GraphRAG and prompt injection. Plus the full series index.
Generative AI in Plain Words: What LLMs Can and Can't Do
Generative AI creates text, images and code by predicting the next word. Here's what that means, and why your company's knowledge is the part it's missing.
Taxonomy: Organize Knowledge So AI Searches Less and Finds More
A taxonomy is a tree of categories. Tagging documents with one lets an AI assistant skip irrelevant content before it searches, which means less noise and more accurate answers.
Engineering
Web, cloud and backend engineering patterns from production projects: Next.js, AWS and databases.
Next.js App Router: A Pragmatic SEO Playbook
How to build SEO-first sites with the App Router - generateMetadata, structured data, ISR, and Core Web Vitals.
Cutting AWS Bills 40%: ECS Fargate Cost Patterns That Worked
Right-sizing tasks, capacity providers, savings plans, and image slimming - the playbook we use across client clusters.
TypeORM + PostgreSQL: Patterns for Real Apps
Migrations, soft deletes, optimistic locking, and the entity patterns we use across production codebases.
Have a product idea or a system to scale?
Tell us what you're building. You'll hear back within one business day - from a senior engineer, not a sales rep.
- Reply within 24h
- Senior engineers only
- Fixed-scope or T&M
- NDA on request