Skip to content

Work with me

Built fast.
Built to stay up.

I build with Claude Code, Codex, and whichever model fits the job. They are tools that carry my speed and my creativity; the architecture, the review, and the accountability are mine. Every line is reviewed, tested, and handed to you with the repo, the docs, and the accounts.

Get a written scope in 48 hours
Rudra Khakhar with liquid chrome poured over his face

How I work with AI

The tools pour on speed.
The judgment is still mine.

I build with Claude Code, Codex, and whichever model fits the day. They draft fast. I decide the architecture, review every line, write the tests that matter, and take the call when something breaks.

Nobody hires a photographer for the autofocus. You hire the eye behind it.

Sounds familiar

  1. The spreadsheet that runs the team has one owner and no backup.
  2. It works for the demo. It has not met a real user.
  3. Two quotes for the same build came back ten times apart.

How I build

The loop is the method.
The tools are not the point.

  1. Spec
  2. Build
  3. Test
  4. Review
  5. Ship
What the AI doesWhat I do
Drafts code from a written specWrite the spec and decide the architecture
Refactors and writes the first testsReview every diff and add the tests that matter
Explains unfamiliar code fastRun evals and security checks, and decide what ships
Switches between Claude Code, Codex, and other models as the task changesPick the tool, direct it, and own the result
Works at 2 a.m.Answer the email at 9 a.m.

No AI in your auth or payments without a test suite around it.

8 builds on this site, each labelled solo or team, synthetic or live93 Lighthouse mobile on this page’s home, 100 desktop, measured 2026-09-05

Six paths, not a grid

Pick the problem.
The scope follows.

Review credits into Build. Build hands off into Keep-It-Running. No prices on this page: you get a written number before you commit to anything.

Proof-of-Work Week

A working thing you can click by Friday.

You get

  • One core flow, built end to end
  • A live URL, with sign-in if the flow needs it
  • The repository and a README your next engineer can follow
  • A short recorded walkthrough
  • A written note on what this build is not

Clock

5 business days. Staging URL by day 3.

Starts with a written scope, not a discovery call.

Ops Tool Build

Replace the spreadsheet that runs your team.

You get

  • A dashboard, registry, or workflow app on Supabase and Vercel
  • Sign-in, roles, and the exports your team already uses
  • A data pipeline from the files you have today
  • Tests on the flows that matter, plus a handoff document
  • 30 days of fixes after handover

Answers-From-Your-Docs Assistant

Cites your documents. Says “I don’t know” when it should.

You get

  • A retrieval assistant over your policies and manuals
  • An embeddable widget for your site or intranet
  • A citation on every answer and a refusal policy for the rest
  • An evaluation set with a pass rate you can re-run
  • A cost ceiling, and a note on where AI is not used

Clock

2 to 4 weeks.

Starts with your documents and twenty questions your team actually asks.

Websites & Frontend Design

A site that looks like nobody else’s and loads before they notice.

You get

  • Visual direction, type, and motion designed for your business, not a template
  • Fast pages that read well on a phone and score well on Lighthouse
  • Generated imagery and 3D where it earns its place
  • A CMS or content structure your team can edit without me
  • Analytics, SEO basics, and a launch checklist

Clock

2 to 4 weeks.

Starts with your current site, your customers, and what you want them to feel.

Custom CRM & Smart Systems

Make the systems you already run talk to each other, and tell you what is happening.

You get

  • A CRM or operations layer shaped around your pipeline, not a vendor’s
  • Integrations with the tools your team already uses: email, calendars, spreadsheets, accounting, ticketing
  • AI where it helps: summaries, triage, next-step suggestions, with a human deciding
  • Dashboards for leaders: team workload, throughput, growth, and what is stuck
  • Roles, audit trail, exports, and a handoff your next engineer can follow

Production Readiness Review

You built it fast. I will tell you what breaks first.

You get

  • A five-day review of an AI-built app: secrets, database policies, auth, tests, deploy and rollback, cost, maintainability
  • A plain-English summary and a ranked list of fixes
  • The checklist I used, so you can run it again yourself
  • A review, not a penetration test or a certification
  • The fee credits toward an Ops Tool Build or an Assistant if I do the fixes

Clock

5 business days.

Starts with read access to the repo and the hosting account.

Keep-It-Running

Monthly fixes, upgrades, and a human who answers.

You get

  • Monitoring and a next-business-day response window
  • Dependency and model upgrades
  • Small changes as your process changes
  • A short monthly note on what changed and what to watch
  • Pause or cancel any month

Clock

Monthly.

Follows a build. It is not sold on its own.

Proof

Things that shipped.

What you own

Everything.
From day one.

You should be able to keep building without me. The handoff is written for the next engineer, not for me.

  • The repository, with its history
  • Documentation and a runbook for the next engineer
  • Hosting, database, and AI-provider accounts in your name
  • The tests, and how to run them
  • 30 days of fixes after handover

Fit

A good fit. Not a fit.

Good fit

  • An ops team with a process it repeats every week
  • A founder with a validated need and a deadline
  • Anyone with an AI-built app that already has real users

Not a fit

  • Regulated payments without a compliance owner on your side
  • “Just make it look nice”
  • A build that needs a team of five

Before we start.

Will it break?

Things break when nobody tests the flows that matter and nobody watches production. Every build ships with tests on the critical paths, a staging URL before launch, and 30 days of fixes. Keep-It-Running covers what comes after.

Who maintains it?

Your team can, because you own the repo, the docs, and the accounts. If you would rather not, Keep-It-Running is a monthly arrangement you can pause or cancel.

Do you use my data to train anything?

No. Your documents and records stay in your accounts. Demos on this site use synthetic data, and any assistant I build for you runs against your own store with the provider settings that keep your data out of training.

What if I want to take it in-house?

That is the plan from day one. Hosting, database, and AI-provider accounts are opened in your name, the repository is yours, and the handoff document is written for the next engineer, not for me.

Why fixed scope?

A fixed scope means you know what you are getting and what it costs before you commit. Hourly billing rewards slowness. When the scope is still taking shape, we start with a Proof-of-Work Week and decide from something you can click.

What about hosting and API costs?

They are yours, in your accounts, and I tell you the expected numbers in the scope. Assistants get a cost ceiling so a busy month cannot surprise you.

Do you use AI for security-critical code?

Not without a test suite around it. Auth, payments, and permission rules get written specs, deterministic code, and tests that fail closed. The model can explain a decision. It does not get to make the rules.

Can you audit something someone else built?

Yes. That is the Production Readiness Review. It covers apps built with any of the AI coding tools, or none. You get a plain-English summary and a ranked list of fixes. It is a review, not a penetration test or a certification.

Scope

Tell me what you have.
I write the scope.

Five fields. You pick the budget band; I never quote before I understand the problem. This opens your email app with the message drafted, nothing is stored here.

Budget band

Or write to rudrak2906@gmail.com. Email only. I reply within one business day.