I ship AI systems the same way a good team ships software: scoped tickets, measured outcomes, no mystery work. Retrieval, agent orchestration, evaluation, and the product surfaces around them.
Details
Sprint stats
221
Repositories
791
Contributions
23
Repos contributed
38
Day streak
ScholarNotesPro — RAG research workspace
NotebookLM-style research app: PDF + YouTube ingestion, inline citations, and generated summaries, timelines, mind maps and study guides.
Daybreak — AI calendar scheduler
A terminal LangGraph scheduler rebuilt as a multi-user web app: per-user Google OAuth, SSE streaming, split-screen chat and agenda.
Persona chat — AI tech-educator simulator
Streaming chat that simulates the teaching style of two Hindi/Hinglish tech educators, with a persona toggle and prompt storage in Postgres.
aniketdev.blog — notebook book-blog
A book-style reading experience: markdown compiled to typed blocks, a page-flip reader, and a FastAPI + Neon backend with a markdown→blocks compiler.
AI Image Editor — masked inpainting & outpainting
Upload a photo, paint a mask over the region to change, describe the edit, and regenerate just that area — plus one-click background removal, style filters, and aspect-ratio expansion.
Auto Review PR
A GitHub webhook triggers an Inngest pipeline that fetches a PR diff, runs it through an OpenAI Agents SDK reviewer, posts the review as a PR comment, and streams live run progress to a Next.js dashboard.
Enterprise SupportOps MCP
AI support assistant and MCP server for support and finance teams: looks up customers, invoices and tickets, opens and updates tickets, and prepares refunds that only move when a person confirms them.
Self-Consistency Answer Engine
Fans one prompt out to OpenAI, Claude and Gemini in parallel, then synthesizes a single answer with Claude — streamed live.
AI Expense Tracker (generative-ui)
Conversational expense tracker with generative UI, JWT auth and per-user data isolation on a persistent SQLite volume.
Architecture decisions I've had to defend, written up after the fact. Each opens with the problem, the trade-off I took, and what it cost.
Showing 8 of 18
Caching is like keeping a shortcut to frequently traveled paths. The application layer is where most REST API caching happens — store…
HTTP methods are the verbs of your API. Stick to their semantic meaning. The URL says what you're working with; the HTTP method says what…
If you build or ship anything that runs on a server, you eventually live inside SSH. It's the door between your laptop and the machine your…
Most of the data we store is happy in a table or a JSON document. A user, an order, a blog post — rows and columns handle those…
Big picture: the journey is User → Web server (CPU) → Inference engine → GPU (the model) → back to User Text is turned into numbers, the…
If you've built one RAG system, you know the demo to production gap intimately. The demo works because you asked a clean question against a…
Most API discussions collapse into "REST vs GraphQL" flame wars and never get to the decisions that actually matter day to day: how you…
As an application grows, a single database stops being enough. You need to spread data across multiple servers — but how you spread it…