I build AI automation that works, and I teach what I learn.

I'm Vitaly Kirkpatrick. I build AI agents and automations that do real business work, and everything on this site is a working demo, not a promise.

I'm Vitaly Kirkpatrick, an AI automation builder. I make AI agents and automations for business, I teach near-infrared spectroscopy, and I write memoir stories. Flip the cards below to read how my public sites work, then visit the ones you like, or press Try a demo for the short story of how I got to full AI autonomy.

12 sites you can flip and visit

Click or tap a card to flip it. Press Learn more for the longer write-up, or open the full work page.

Search Engine Seer

An SEO audit tool that shows a source for every score, plus a check of what AI answer engines say about a site.

Huecraft

A brand identity generator that turns a short brief into a whole identity, not just a logo: logo suite, colour with contrast proof, type, voice and a brand guide.

ZoneVouch

A domain availability checker that asks the registry, shows the registrar's real register and renewal price, and writes a diligence report that lists what it could not check.

ChartedStories

Data stories with every number cited: ask a business question and get a readable report with narrative, charts and tables, and a source on every number.

SourcedCharts

Charts where every number shows its source. Build them in the editor or call the API, and each value links back to where it came from.

Everyably

Fix accessibility, not just the checklist: a real WCAG scanner, code fixes you approve line by line, and AI-drafted legal documents. It audits its own site, live.

Spectra Lab

Check an NIR calibration before you trust it: free validation tools, three guided journeys on real data, and a browser lab for PLS calibration.

SpectroScience

My NIR spectroscopy online course: 32 lessons on calibration, chemometrics and real-world applications, in plain words and far cheaper than vendor training.

VidRevive

An AI video studio that transforms existing videos into structured courses with narration, branded slides and motion graphics.

DeckSpeaksAI

Turns course slides into narrated videos that sound like you: upload a deck, keep your voice, get a finished lesson video.

Lodestake

Name and domain decisions with the research attached: a name is tested, the domains are checked, and the reasons are written down before anyone buys.

ManuscriptSmith

An AI writing studio for authors. It learns how you write, so the book still sounds like you from the first chapter to a publish-ready file.

Watch

My videos and the VitalyBook channel: stories from my life told as drawn animation, and short lessons on near-infrared spectroscopy.

YouTube channel

Choose your door

BuildLive demos of AI agents and automations. TeachNIR spectroscopy courses on SpectroScience. ReadVitalyBook: the memoir and stories. Say helloSend me a note.

How the machine works

Four short animated explainers. They play when you scroll to them. Press Play to watch again, or tap a numbered dot to jump to a step.

From ask to done

Press Play, or tap a step.

You ask for something in plain words. No forms, no jargon.
The ask becomes a ticket, so nothing lives only in someone's head.
A plan appears: what will be done, in what order, and what it might cost.
Money or a customer email? The gate stops everything until a human says yes. Even robots need a permission slip.
Approved. An agent does the work, one careful step at a time.
An evidence check asks for proof: a file, a screenshot, a passing test. A promise is not proof.
Done, with the receipts attached. Nobody has to ask whether it really happened.

Every job here follows the same road, so nothing gets lost and nothing surprises you. It starts with a request in plain words. The request becomes a ticket, a written record with an owner and a status. Next comes a plan that lists the steps, the order and the likely cost. Most plans move straight on. Two kinds never do. Anything that spends money, and anything that sends an email to a customer, stops at a human gate until a person approves it. Once the gate opens, an agent does the work. Then a separate evidence check looks for proof, such as a saved file, a screenshot or a passing test, before the ticket is allowed to close. The ticket keeps the whole trail, so you can see who asked, what was planned, who approved and what was delivered. That is how automation stays fast without becoming reckless: speed for the routine parts, and a human hand on the parts that matter.

Weigh first, then pour

Press Play, or tap a step.

Jobs arrive, some easy and some hard. From the outside they all look alike.
Before any model is used, a quick weigh-in sorts each job by difficulty.
Easy jobs, like sorting, renaming and summarizing, go to small cheap models. Fast, and good enough.
The one hard job goes to a big model, because that is where money is well spent.
The cost meter stays low. Penny, who fainted at a $12 day, finally naps.

Not every job needs the biggest brain in the building. One day the AI bill hit $12 because every task, easy or hard, went to the most expensive model. That is like hiring a crane to lift a coffee cup. The fix is to weigh first, then pour. Each job gets a quick look at how difficult it is. Routine work, such as sorting files, renaming things or writing a short summary, goes to small, cheap models that finish quickly and cost very little. Genuinely hard work, such as untangling a messy plan, goes to a large model that can think longer. The cost meter shows the result: the same amount of work, a small fraction of the spend. Penny the piggy bank, who once fainted at the bill, now sleeps through the day. Cheap where it can be, careful where it must be.

Agents that check each other

Press Play, or tap a step.

A builder agent gets a job: make the weekly report file.
The builder replies, OK, done! It sounds confident. Confidence is free.
A reviewer agent does not take its word. It opens the folder. The report file is not there.
The reviewer sends the work back with a clear note: claimed, not delivered.
The builder tries again, and this time the file really lands in the folder.
The reviewer checks again, sees the file, and passes it. Now OK means OK.

An AI agent can say a job is finished when it is not. It is not lying on purpose; it simply reports what it meant to do. That is why building and checking are two different jobs done by two different agents. The builder makes something and says it is done. The reviewer never relies on that claim. It opens the folder, looks for the file, runs the test or loads the page, and compares what it finds with what was promised. When something is missing, the work goes back with a plain note about what failed. The builder fixes it, the reviewer looks again, and only then does it pass. This costs a few extra seconds and saves a lot of embarrassment. Trust comes from evidence you can see, not from a cheerful message. In this setup, a claimed OK does not count until someone has checked it.

How a website builds itself

Press Play, or tap a step.

Research first: what do people search for, and what do they need to understand?
A plan sets the page list and what each page must say.
Pages get drawn, one panel at a time, before anyone writes code. Erasing a pencil line is cheaper.
Screenshots at phone and desktop width show what a visitor would really see.
Fixes follow: text that clips, buttons that crowd, gaps that look odd.
A review page collects the screenshots so the founder can approve or push back.
Only after a yes does it publish. Until then it is a private preview.

A website here is built in a fixed order, and each stage leaves something you can inspect. Research comes first: what people search for and what they need to understand. The plan turns that into a list of pages and the job each page must do. Then the pages are drawn as simple panels, before any code is written, because changing a drawing is cheap. Screenshots are taken at phone width and at desktop width, since most visitors arrive on a phone. Anything that looks wrong gets fixed, such as clipped text, crowded buttons or odd gaps, and then new screenshots are taken to confirm the fix. All of it is gathered on a private review page, where the owner can approve each part or ask for changes. Publishing happens last, and only after a clear yes. Until then, nothing is public.

AI automation for small business

What it means

AI automation for small business means taking the jobs that repeat every week and letting software do them. Think of answering the same customer questions, sorting incoming leads, writing first drafts of quotes, updating records, and building the weekly report. A person still decides what matters. The software does the repeated typing, copying and checking, and it never asks for a long lunch.

Where to start

Start with one job that costs you an hour a day. Write down the steps. If a new employee could follow them with a checklist, an automation can too. Build that one first, watch it for two weeks, then add the next. Small steps keep the cost low and the risk small.

What I build

I build AI automations and the agents that run them: workflows that connect your email, CRM, spreadsheets and documents, with a human approval step wherever a mistake would be expensive. The proof today is my own platforms, shown in the demos above. I do not have client case studies yet, and I would rather say so than invent them.

AI agents for business

What an AI agent is

An AI agent is software that is given a goal, picks the steps, uses tools, and checks its own result. A chatbot answers a question. An agent finishes a task: it searches, drafts, files, sends for approval, and reports back. For a business, that difference is the point. A chatbot talks about the work; an agent does it, which is more than some meetings manage.

Why a team of agents

One large agent that does everything is hard to trust. A team of small agents, each with one job and a record of what it did, is easier to test and easier to fix. My own agent fleet works this way: a planner, a builder, a checker and a reviewer, with a task board that shows who did what.

Keeping people in charge

Good agents know their limits. Safe changes can be approved by a decision layer. Risky ones, such as spending money or sending a message to a customer, go to a person first. That rule is built in from the start, not added later. If you are exploring AI agents for your business, ask any builder how it works, and ask to see the log of what an agent actually did.

Say hello

Have work that repeats every week, or just a question? Send me a note.

Say hello