I'm 19. For the past year I've learned AI every day and used it to build real things for real businesses. Tap any section to see what it took.
What I've built
ReviewTapReview cards built in a week, 10 sold by cold message
An NFC and QR card that sits on a business's counter. A customer taps it with their phone and lands on the business's Google review page.
What it took: I built the whole product in about a week: the card design, the website, logging every tap, and a dashboard where the owner sees taps and reviews. Unhappy customers can leave private feedback, so the owner hears about problems and can fix them. Emails go out automatically through Resend, and the data lives in Supabase.
How I sold it: I made a list of 373 Latvian businesses and scored them by priority, then messaged about 100 businesses I didn't know on WhatsApp. About 20 replied and 10 bought, mostly clinics, plus tow and car transport companies. I invoiced them myself.
My own cold email systemInboxes, lead data and an AI SDR in progress
What it took: I set up my own Google Workspace sending inboxes on my own domains, with SPF, DKIM and DMARC, and warmed them up for three months before sending.
I find and qualify leads with data from Treg (a prepaid data API) and Apify scrapers, send through Salesforge (before that Instantly), and track every lead and reply in Twenty CRM, with a booking link for calls.
Now building: an AI SDR, a team of agents that finds and checks leads, writes each message, handles replies and books calls.
AI automation for an accounting firmSaves the team about 15 hours a month
Client due diligence: under Latvia's anti-money-laundering law (NILLTPFN), outsourced accountants must research every client and keep the files for at least five years. For a firm with 92 clients, I built tools that pull each company's data from the business register and prepare those files as Word documents: identity, beneficial owners, type of business, risk level and sanctions checks.
Inbox Clerk: reads an emailed order or quote, turns it into rows for the accounting system and drafts the reply.
Result: about 15 hours of work saved every month.
Latvian company scanner3,779 companies from free government data, €0 data cost
What it took: a scanner that reads Latvia's open government data (tax records, the business register and filed annual accounts) and estimates where each company is losing money.
Result: 3,779 companies with 5 to 80 staff mapped at €0 data cost, so a first message can start from a number about their own business.
AI outreach pipeline, built as an agent teamResearches, writes, fact-checks and reviews every message
What it does: for every lead it researches the company, writes the message, checks each fact against its source, and a separate reviewer agent passes or blocks the message before anything is sent.
How it's built: in Claude Code, with MCP servers for tools and data. A cheap model (Haiku) does the checking, a stronger one (Sonnet) the writing. The AI only proposes; plain code checks the data and does the actual sending, with hard limits on daily spend. Every run is logged.
The agents also draw on a knowledge base I made from about 90 business books.
Inbound email assistantSorts incoming email and drafts the replies
Reads incoming email. A small model sorts the message and the sender, a stronger model drafts the reply, and anything unclear is flagged to me instead of answered.
Proof
SEB School Ambassador programmeTop level Everest, 8 lectures, now a mentor
In 11th grade I learned investing, saving and entrepreneurship, gave 8 lectures on money to other students and finished at the top level, Everest. The same year I shadowed the programme's director. This school year I'm back as a mentor for new ambassadors.
ViA Youth Innovation ForumVidzeme University of Applied Sciences, Feb 2025
Took part in the youth innovation forum at Vidzeme University of Applied Sciences on 27 February 2025.
More about me
Tools and knowledgeClaude Code, MCP, agent teams, APIs and more
AI: Claude Code, MCP servers, sub-agents and agent teams, evals and verification loops, skills, computer and browser use, scheduled tasks, RAG and vector search, knowledge bases for agents, context and prompt engineering.
Building: APIs and webhooks, Python, Git and GitHub Actions, VS Code, Supabase, Resend, Zapier.
Sales and data: Google Workspace admin, inbox warm-up, SPF, DKIM and DMARC, Salesforge, Instantly, Twenty CRM, Treg, Apify.
Outside workBench press 120 kg, marathon under 4 hours, 20+ books
I taught myself to train: five years of weights (bench press 120 kg), three years of running, a Rimi Riga Marathon under four hours and three years of volleyball. I built my own home gym and taught my cousin to train. Sport taught me that results come from doing the same thing every day, even when I don't feel like it.
I've read 20+ books on psychology, sales, self-improvement and finance. The two that shaped me most: Can't Hurt Me and The Success Principles.