IST
Filed from the builders

Abhinav Raj

I build AI tools, web systems, and product interfaces that make messy ideas easier to use, explain, and ship.

  • 5Shipped products
  • 27+Verified credentials
  • 3Focus areas
Editorial portrait of Abhinav Raj
Photographed at the desk · Vol. 1, No. 1
About Me

Build cleanly
Test quickly
Keep it useful
Keep the magic explainable

I work where product, engineering, and design keep interrupting each other. The goal is simple: interfaces that explain themselves, systems that hold up under real users, and AI features that stay useful after the demo.

The path so far has moved from privacy tools and file workflows into model gateways, agents, retrieval, and the practical plumbing that makes AI products behave in public.

I am not trying to make the work sound larger than it is. I am trying to make useful things, leave clean decisions behind, and avoid building software that needs a tour guide.

Now

CLEX AI

Building one endpoint for model access, routing, keys, usage visibility, and playground testing, because every app eventually asks: which model today?

Recent

Privacy and utility tools

Recently shipped privacy and utility work across file movement, disposable mail, receipt parsing, and race-weekend intelligence. Strange mix, useful pattern.

Learning

Machine learning systems

Working through ML systems material while turning the theory into product infrastructure that survives contact with users.

Open to

Useful collaboration

AI builds, product engineering roles, prototypes, and projects where design and engineering need to sit at the same table.

See the work Or send a brief
By Abhinav Raj · Product Engineer

AI Builder

  • LLM workflows, agents, and model gateways
  • Automation for bounded, repeatable project work
  • Human-reviewed outputs with clear fallbacks

Full-Stack Developer

  • Frontend systems with clean product flows
  • APIs, auth, storage, and edge deployment
  • Prototypes structured to grow into products

Intelligent Web Experiences

  • Editorial interfaces with useful motion
  • Privacy-aware tools and thoughtful data handling
  • Project pages that explain the work clearly
Builder
Notes from the bench
Ideas currently misbehaving

Agentic tools

I use agents for bounded work such as research triage, document parsing, UI QA, code review, and repeated project operations. The useful pattern is a clear input, a narrow output, and a verification step.

Privacy by design

For file movement, mail, and AI tooling, privacy starts in the architecture. I avoid unnecessary storage, keep permissions explicit, minimize data collection, and make it clear what leaves the device.

Interfaces with restraint

I keep interfaces focused on the action that matters. Motion, typography, and visual effects should guide attention instead of competing with the workflow.

Human first AI

AI should make a product easier to trust and operate. I design AI features with clear fallbacks, editable outputs, visible reasoning where useful, and controls that keep the final decision with the user.

Selected
Builds

Slide through five builds