How this works

AI assistant for Dhavan’s published portfolio material. Answers can be incomplete or wrong, so do not submit confidential code or data.

Your questions go through Hugging Face, and a model run by DeepInfra writes the answers. Chats may be retained for about 30 days to operate, debug and improve the assistant; DynamoDB TTL deletion is approximate. Formspree processes contact and hire-form submissions. Details are in the privacy policy.

Use the suggested questions or ask about published projects, credentials, and engagements.

Independent AI engineer for software companies

Take your AI agent from demo to production ready.

If your AI gives wrong answers, runs up surprise bills, or nobody can explain what it did, I find what’s blocking launch, fix it, and hand it over to your team.

Tell me what’s blocking you How it works: starts at $5,000

Dhavan Shah You work directly with me. The first 30 minute call is free, and if I can’t help, I say so before you pay anything.

20+ customer workflows at DevRev · MSc Data Science, University of Zurich · Top 0.5% on Kaggle · Founder, KazenAI

20+ customer workflows at DevRev · MSc Data Science, University of Zurich · Top 0.5% on Kaggle · Founder, KazenAI

The problem

A demo only has to work once. Customers need it to work every day.

These aren’t stories about bad teams. They’re what shows up once real people depend on the product, and all four are on the public record.

Cost

“We are currently losing money on OpenAI Pro subscriptions! People use it much more than we expected.”

Sam Altman, CEO of OpenAI, on its $200 a month plan, January 2025. Six months later, Anthropic announced weekly limits on its plans, saying “one user consumed tens of thousands in model usage on a $200 plan.”

Sources: ITPro · Anthropic’s statement, quoted by Simon Willison

Could one customer cost you more than they pay?

A spending limit per customer

Each supported model call is checked against that customer’s limit before it runs. It starts in shadow mode, which only watches, so nothing is blocked until you trust it.

This is us

Accountability

A tribunal held Air Canada responsible for what its chatbot told a customer.

The chatbot gave wrong advice about bereavement fares. The airline argued it wasn’t liable for its chatbot, and the tribunal rejected that. The award was small, about $812 with interest and fees, but the airline still had to answer for it.

Sources: McCarthy Tétrault · Dentons, on Moffatt v. Air Canada, February 2024

When your AI gets it wrong, can you show what happened?

A receipt for every decision

Every model call allowed or stopped, with the customer, workflow and run behind it, and a timeline for every run.

This is us

Wrong answers

Cursor’s support bot invented a policy, and users said they were cancelling.

It told a customer the product worked on one device per subscription. No such rule existed. The company later called it “an incorrect response.” How many people actually left isn’t known.

Source: CX Today, April 2025

Do you know how often yours gets it wrong?

A measured failure rate

A test suite built from your real traffic runs on every change, so you know how often it fails and whether a fix helped.

This is us

Access

A flaw in Asana’s AI connector could show one customer’s data to another.

Asana told BleepingComputer about 1,000 customers were affected. It was a logic flaw, not a hack, and the report shows no evidence the data was misused.

Source: BleepingComputer, June 2025

Can you prove each user only sees what they’re allowed to see?

Permissions enforced and tested

It only reads what each user may see. It cites its sources, or says “I don’t know” when the evidence isn’t there.

This is us

If one of these could happen to you, that’s where we start.

The first 30 minute call is free, and I reply within one business day.

Tell me what’s blocking you

One outcome: AI you can put in front of customers.

How it works

Check it, fix it, keep it working.

Prices in USD. Remote. Fixed scope and written deliverables, not open ended billing.

1 · Check Start here

Production Readiness Diagnostic

$5,000 fixed · 2 weeks

I go through your traces, logs and billing, then give you a written report: is it ready, what’s blocking it, and what to do next. Read access only to start; nothing changes in production. Start a Pilot within 30 days of the readout, and 50% of the fee ($2,500) is credited against it.

2 · Fix

Production Pilot

Typically from $18,000

I build the agreed work from a written proposal with options. It starts narrow and is tested before it reaches customers. Your team keeps the code, tests and runbooks, so you don’t depend on me afterwards.

3 · Keep it working

Monthly partnership

Optional · after a Pilot

One focused track a month on whatever is slipping now: a new workflow, a cost regression, a failure that came back. It continues only while it keeps paying for itself.

In two weeks, you know what’s stopping your launch.

The $5,000 Diagnostic ends with a written report that answers three questions. This is what one looks like, with example findings.

Production Readiness Diagnostic report

Example, not a client result

1 · Is it ready?

Not yet. Two things are blocking launch.

  • How often does it get things wrong?

    Blocking launch

    Nobody knows. It’s only spot checked.

  • Could you stop one customer’s runaway bill?

    Blocking launch

    No. Spend is only visible per month, in total.

  • Can you show what happened when it went wrong?

    Needs work

    Partly. Logs exist, but can’t be tied to a customer.

  • Does each user only see what they’re allowed to?

    In place

    Yes, and tests prove it.

2 · What’s blocking it?

  1. 1

    No limit per customer

    A few accounts could wipe out your margin.

  2. 2

    No measured failure rate

    Customers will find the failures before you do.

3 · What should you do next?

  1. A

    Fix the two blockers

    Add spending limits, and a test suite built from your real traffic.

  2. B

    Fix all three gaps

    Option A, plus a receipt for every decision.

Start a Pilot within 30 days of the readout, and 50% of the fee ($2,500) is credited against it. Read access only to start; nothing changes in production.

Diagnostic payment: 100% upfront, or 50% on start and 50% before the final readout. Pilot milestones are set in the proposal. Want only the KazenAI product, with your team doing the integration? kazenai.com

Why me

You work with the person who built it.

I am an independent AI systems engineer. I take LLM features and agents from demo to dependable production: measured reliability, a spending limit per customer, and a record of every decision.

Dhavan Shah

Track record

20+
customer workflows where I architected production LLM features at DevRev
Top 0.5%
Kaggle Competitions Expert: 701 of 203,686
~2,500
automated tests across the KazenAI product
MSc
Data Science, University of Zurich

Before DevRev, I did applied AI work with AXA XL and Sulzer in Zurich.

KazenAI is the product I built from this work. Clients can use it; it’s never required. KazenAI is a product, not a consulting service. Under the engagement agreement, what I build for you is yours, KazenAI stays mine, and your code, systems and confidential data never go into it.

[email protected] LinkedIn GitHub KazenAI Full experience

I’ve already built the tools for this.

I don’t start from zero. I built these for exactly these four risks, and they’re how the Pilot gets delivered. Built by me, not client case studies. Agent FinOps is KazenAI’s product; run receipts are part of it.

Spending limits per customer 20 allowed, 30 denied, $0.00 over. A recorded test: 50 concurrent agents against one $5 budget. KazenAI Agent FinOps checks every supported model call against the customer’s limit before it runs. About 2,500 automated tests across the product. Run receipts A receipt for every allow and deny. Part of Agent FinOps: a timeline for every run, connecting cost and limit decisions to the calls, retries and incidents behind it.

Supporting capabilities

See all technical work

Is this for you?

Best when customers are about to depend on it.

Strongest fit: an AI feature or agent your customers use, in production or close to it, with a technical owner.

Good fit

  • A launch, a large customer, or a pricing change depends on the agent behaving.
  • Model spend or failures are growing faster than your confidence in them.
  • You can share traces, request logs or billing exports under scope.

Not a fit

  • Idea stage demos with no real users yet.
  • Open ended staff augmentation without a defined outcome.
  • Guaranteed savings figures, compliance certification, or work outside agreed scope.
Tell me what’s blocking you

The first 30 minute call is free. No obligation until you approve the Diagnostic.

Next step

Tell me what’s blocking you.

This form is for consulting enquiries. I reply within one business day, and if there’s a fit, I send a private link for a free 30 minute call.

The problem
What’s blocking your launch?

What happens, how often, and what you’ve tried. For example: it fails on 1 in 10 real tickets, or model spend tripled while revenue grew 20%. Nothing confidential, please: no code, credentials or customer data.

When do you want to start?
About you

Formspree processes submissions.

Brief received

Thanks. I’ll reply within one business day. Nothing is booked or charged yet.

Looking for the KazenAI product? Book a margin review on kazenai.com. Prefer email? [email protected]