PV/26

Pulkit Verma

AI Engineer, frontend-minded systems builder

Selected portfolio / 2026

Building deterministic AI systems with a frontend eye for clarity.

I work on agentic workflows, productized AI systems, and polished interfaces that make complex software feel inevitable.

See selected work Read technical notes
Current Scaling AI at Setu
Building Products, tooling, and notes
Focus Reliable agentic systems

Principles

Determinism > randomness

Agentic SDLC, not AI theater

Zero-hallucination is a systems problem

What you can pull me in for

01
AI product systems

Workflow design, orchestration, eval loops, and shipping paths.

02
Frontend for technical products

Interfaces that reduce cognitive load while still feeling sharp.

03
Engineering leverage

Review automation, internal tooling, and systems that scale teams.

Featured builds

Projects, products, and engineering systems

The best entry point is a mix of shipped product, internal leverage, and infrastructure thinking. These cards should make that legible in under a minute.

01 AI systems / product

weaveai.dev

Production-oriented AI agents and RAG systems designed for teams that need reliability, not demos.

Role: builder Focus: reliability
Agentic workflows RAG Production UX
View case study External
02 Tooling / browser UX

trufeed.app

Visual feedback capture with browser context, built to reduce the drag between finding issues and shipping fixes.

Browser UX Feedback loop
Open project External
03 Developer tooling

Sensei

AI-powered code review CLI for GitLab MRs. Learns your review style and applies it consistently using Claude Code.

Python CLI
Open repo External
04 Developer tooling

Branchwise

Branch-scoped memory for Claude Code. Each git branch gets its own context — auto-loads on session start, swaps on checkout, zero config.

TypeScript MCP Claude Code plugin
Open repo External
05 Developer tooling

Review Agent

Autonomous code review against team principles, pushing AI into the quality loop of the SDLC.

Code quality Automation
See details External
06 SEO / content infra

seo-engine

I/O-agnostic SEO content engine that discovers keywords, scores them with an LLM, and generates publish-ready blogs through pluggable adapters.

TypeScript LLM adapters
Open repo External
07 Architecture / infra

RAG Foundation

Retrieval-first architecture work aimed at reducing hallucination through system design, not prompt tricks.

Architecture Retrieval
Read framework External

“The interesting work isn’t making AI talk. It’s making AI behave.”

Technical notes

Short writing on systems, frontend clarity, and AI behavior

This should feel like a working notebook, not a generic blog. Fast to scan, opinionated, and worth bookmarking.

Note 01 Agent design

Deterministic agents need explicit state, not better vibes

A piece on why most agent failures are orchestration failures: weak state boundaries, vague retries, and invisible handoffs.

Systems design State management
Read note
Note 02 Frontend systems

Interfaces for complex products should feel calm, not clever

Notes on using editorial hierarchy and restraint in technical interfaces.

Read note
Note 03 RAG

Zero-hallucination is an infrastructure stance

Retrieval quality, chunking, and evaluation loops matter more than prompt folklore.

Read note

Browse archive

Technical notes, field essays, and build breakdowns

A full notes index can become the long-tail trust layer of the site.

View all notes

Resume snapshot

Frontend engineer with strong AI systems range

The site can frame you as a systems builder first, while the resume can sharpen the frontend engineering story for hiring and outbound.

Open PDF resume Start a conversation