# About Artyom Zankevich I'm an AI engineer and engineering leader at Akveo in Vilnius. I prototype AI agents myself, then lead the 30+ engineers who ship them. In my department, commits written with AI tools rose from 6% to 74%. - Current roles: AI Engineer and Head of Web Development at Akveo - Based in Vilnius, Lithuania, remote - Updated Oct 2026 ## AI in Engineering Since 2024 I have been moving the department to AI-assisted development, with the same review and tests for code written with AI tools. - Q1 2024: 6% of commits written with AI tools - Q2 2024: 8% of commits written with AI tools - Q3 2024: 10% of commits written with AI tools - Q4 2024: 13% of commits written with AI tools - Q1 2025: 16% of commits written with AI tools - Q2 2025: 20% of commits written with AI tools - Q3 2025: 27% of commits written with AI tools - Q4 2025: 38% of commits written with AI tools - Q1 2026: 52% of commits written with AI tools - Q2 2026: 64% of commits written with AI tools - Q3 2026: 74% of commits written with AI tools The share of the department's commits by quarter. Commits that name an AI co-author are only a floor, since tools like Cursor and Copilot leave no trace. ## Projects I keep client names private and describe each project by what it was and who used it. ### Order Confirmation Agent AI prototype for a distributor's purchasing team. AI engineer, Akveo, 2026. Buyers checked supplier order confirmations against purchase orders by hand, line by line. - Extracted order lines from supplier emails and PDFs with structured outputs - Matched them to purchase orders with RAG over the product catalog, and flagged every mismatch - Prepared the matched orders for SAP import, with a review screen for the buyer Outcome: A working prototype in 3 days, where a proof of concept used to take 4–6 weeks Stack: Anthropic Claude, Structured outputs, RAG, TypeScript, NestJS, PostgreSQL, Supabase ### Voice Support Agent AI prototype for an electric vehicle charging network's driver support. AI engineer, Akveo, 2026. Drivers call support when a charger fails, in many languages and at any hour. - Built an agent that answers drivers by voice in their own language, on the OpenAI Realtime API - Gave it tools through MCP to check a station, restart a charging session and open a ticket - Handed the call to a person, with a summary, when the agent could not help Outcome: Demoed to the prospect as a working product before the contract Stack: OpenAI, Real-time voice, Tool calling, MCP, TypeScript ### Proposal Plugin Internal pre-sales tool on Claude Code and Codex. AI engineer, Akveo, 2026 – now. Every proposal started from a blank page and took days of back and forth. - Designed skills that shape a solution with the proposal author, then build the proposal from it - Pulled sources from the CRM and team chats through MCP, and similar cases from the department's library with RAG - Rendered a reviewed HTML proposal with an optional PDF on the approved templates Outcome: Brief to first draft in 1 day instead of 3+; used on 6 pre-sales deals in the first three months Stack: Claude Code, Codex, MCP, RAG, Prompt engineering ### Engineering Workflow Plugins Plugins and skills for Claude Code and Codex. Lead engineer, Akveo, 2025 – now. Teams repeated the same setup, review and documentation steps by hand on every project. - Built Claude Code and Codex plugins and skills for project setup, code review and documentation - Added an MCP server for YouTrack, so agents read and update the tasks they work on - Kept each plugin to one job, with a usage guide Outcome: Part of every team's daily workflow Stack: Claude Code, Codex, MCP, TypeScript ### AI Adoption Program A change in how the whole department builds. Program lead, Akveo, 2024 – now. Make AI-assisted development a normal, reviewed part of how every team works. - Picked the tools and rolled them out team by team - Wrote guidelines on what to use AI for and how to review its output - Measured the effect on speed, quality and cost Outcome: Commits written with AI tools went from 6% to 74% across a 30+ engineer department, 2024 to 2026 Stack: AI adoption, Claude Code, Codex ### AI Interview Coach iPhone app for interview practice. AI engineer, Personal, 2026 – now. Practice a job interview for a specific role and get honest, consistent feedback on every answer. - Built the voice interviewer on the OpenAI Realtime API - Scored answers against versioned rubrics with structured outputs, and checked every prompt change with evals - Wrote the native SwiftUI app and its NestJS and PostgreSQL backend Outcome: In TestFlight beta Stack: OpenAI, Real-time voice, Structured outputs, Evals, Swift, SwiftUI, NestJS, PostgreSQL, Railway ### Language Tutor Plugin Open-source plugin for Claude Code and Codex. Engineer, Personal, 2026 – now. Turn my own textbooks and audio into lessons an AI tutor can prepare and review. - Built skills that prepare each lesson from local textbooks and audio and keep progress between sessions - Added a short recap after each lesson for later review Outcome: Open source on GitHub Stack: Claude Code, Codex, Prompt engineering ### AI Meetups at Akveo Weekly talks and hands-on sessions for Akveo engineers. Co-organizer and speaker, Akveo, 2026 – now. Engineers needed a place to learn AI-assisted development from each other's projects. - Co-organized the program and gave talks and demos - Showed cases from the department's own projects instead of vendor demos - Kept notes and recordings in the knowledge base Outcome: 12+ sessions Stack: AI adoption, Claude Code, Codex ### Internal Tools Small apps for Akveo's own operations. Engineer, Akveo, 2025 – now. Routine work in hiring, time tracking and billing took hours of manual steps every month. - Built a time log calendar widget for YouTrack and an app for monthly invoices and time reports - Synced job openings from the hiring system to the careers page Outcome: About 20 hours of manual work saved a month Stack: TypeScript, Next.js, React, Cloudflare, Claude Code ### Hiring and Onboarding Practice How the department hires and onboards. Hiring lead, Akveo, 2021 – now. Hire and onboard fast without lowering the bar while the department doubled. - Set a technical assessment with a clear bar, now with AI-aware tasks - Wrote an onboarding plan for the first weeks - Matched engineers to projects, cutting the time to staff one from 21 to 7 days Outcome: 75+ engineers brought in Stack: Hiring, Engineering management ### Emergency-Travel Membership Healthcare app for web, iOS and Android. Team lead, Akveo, 2019 – 2021. Members of an international medical-transport program manage plans, dependents and billing from anywhere. - Led the frontend and mobile team, and built the member portal and the mobile app - Turned client requests into specifications the team could estimate - Reviewed the user experience and improved it Stack: Angular, Ionic, Capacitor, NgRx, Nebular, AWS ### Machine Learning Workflow Platform Web platform for machine-learning teams. Senior engineer, Akveo, 2019. A Silicon Valley startup's platform for machine-learning and deep-learning workflows needed a fast, server-rendered interface. - Built the frontend and improved the user experience - Added server-side rendering with Angular Universal Stack: Angular, Angular Universal, Angular Material, Nebular ### Home-Services Marketplace Consumer marketplace on the web. Senior engineer, Vention, 2018 – 2019. Match thousands of customers a week with vetted cleaners and handymen through a 60-second booking flow. - Built frontend and backend features - Implemented the interface from the designs - Improved SEO on the public pages Stack: Ruby on Rails, React, JavaScript ### In-Store Rewards and Referrals Rewards web app for small shops. Engineer, Vention, 2017. Give small shops a digital rewards and referral program with automated marketing. - Upgraded Ember.js and the authentication flow - Built frontend features Stack: Ember.js, JavaScript ### Web Trading Platform Browser trading platform for active traders. Senior engineer, Vention, 2016 – 2017. Active traders need real-time markets, charting, trading and news in the browser without lag. - Estimated the work and reported on progress across the full cycle - Changed the architecture for real-time data - Refactored the app and made it faster Stack: Angular, TypeScript, WebSockets, Karma ### Talent Booking and Scheduling Booking app for the talent industry, on iOS, Android and web. Team lead, Vention, 2015 – 2016. Agencies and models schedule appointments and events from one app on phones and the web. - Led the full development cycle, with reports and estimates - Released to the App Store and Google Play - Reviewed code and ran maintenance and support Stack: Ruby on Rails, Angular, Ionic, Cordova, RabbitMQ ### Research Data Crawler Data pipeline for a research-information product. Engineer, 1science, 2014 – 2015. Extract research texts from web sources automatically and at scale. - Designed and maintained Scrapy crawlers - Ran distributed extraction on Scrapinghub - Made the crawlers faster and easier to scale Stack: Python, Scrapy, XPath ## Engineering Leadership I run web engineering at Akveo, its largest production department. I hire engineers, decide who works on which project and make sure the work ships. Since I took it over in 2021 the department has worked on 70+ client projects, 15 to 19 of them at any time. ### Results: People - Engineers in the department: 15 → 30+ (Since Aug 2021, with the same hiring bar) - Average time in the department: 1.8 years → 3.4 years (Jan 2024 to Oct 2026) - Engineers brought in a year: 13 → 19 (In-house and partner engineers, 75+ since 2021) ### Results: Delivery - Bench time: 9% → 4% (Share of engineer time between projects, 2023 to 2026) - Billable utilization: 73% → 92% (Share of engineer time on client work, 2021 to 2026) - Time to staff a new project: 21 days → 7 days (From signed contract to a team on the project) ### Results: AI - Commits written with AI tools: 6% → 74% (Share of all commits, 2024 to 2026) - Time to a working AI prototype: 4–6 weeks → 3 days (A pre-sales proof of concept, built with AI agents) - Client proposal, from brief to draft: 3+ days → 1 day (With the proposal plugin) ## How I Work - **Small Loops.** Build a prototype in days, then decide based on what it shows. Before a big commitment, I try the risky part first. - **Evaluate, Then Ship.** An LLM feature is ready when its evaluation says so, not when the demo works. Before launch, an AI feature has test cases with known answers, a cost per call and a fallback. - **People Own the Result.** AI can write the code. A person still answers for it. Every change goes through the same review and tests, whoever or whatever wrote it. - **AI Where It Pays.** Start where the gain can be measured, check it, and only then scale. Each new AI tool starts with a baseline and one number it has to beat. - **Estimate Honestly.** Show the range, the assumptions and the risks from the first day. Every estimate I send has a range and its three biggest risks. - **Teams before Plans.** A strong team with clear goals beats a clever plan. I match engineers to projects by their skills and what they want to learn, not just by who is free. ## Experience ### AI Engineer, Akveo Aug 2025 – now. Hands-on work on AI agents, voice agents and tools for engineers, alongside running the department. - Voice and order-matching agents for pre-sales, built as working prototypes before the contract - Claude Code and Codex plugins in daily use across the department - A proposal plugin that cut brief to first draft from 3+ days to 1 day ### Head of Web Development, Akveo Aug 2021 – now. Leading Akveo's largest production department of 30+ web engineers, including hiring and staffing. - Scaled the department from 15 to 30+ and brought in 75+ engineers - 70+ client projects since 2021, with bench time down to 4% - Moved every team to AI-assisted development; commits written with AI tools rose from 6% to 74% ### Software Engineer, Akveo Mar 2019 – Jul 2021, senior and team lead. Frontend and mobile work on client products, and team lead on the healthcare membership app. - Led the frontend and mobile team on a membership app - Server-side rendering in Angular for a machine learning platform ### Software Engineer, Vention May 2015 – Mar 2019, senior and team lead. Four products in four industries, among them cross-platform mobile apps and a real-time trading frontend. - Team lead on a cross-platform mobile scheduling app - Real-time trading interface on WebSockets - Fullstack Ruby on Rails and React for a marketplace ### Software Engineer, 1science Dec 2014 – May 2015, contract. Distributed web crawling for a research-information product. - Scrapy crawlers at scale ## Contributions and Training ### FlexGet Content automation tool. Open source, 2026. My open-source contributions include FlexGet, a Python tool for collecting and downloading content such as podcasts, comics and series. It connects RSS feeds, websites and other sources through plugins, with configurable rules that filter content and pass it to download tools. [FlexGet on GitHub](https://github.com/Flexget/Flexget) ### Management Skills Development Program Stratoplan Management School. Training, Oct 2024. The program covered the manager's role during growth and development crises, motivation and feedback, and constructive confrontation in difficult conversations with employees. It combined theory with practical work. [View Stratoplan certificate (PDF)](https://stratoplan-school.com/cert/corp/2024/akveo/Artyom_Zankevich.pdf) ### Nebular Angular UI library. Open source, 2020. I worked on Nebular, an Angular UI library for building applications with reusable components and a consistent design. Based on the Eva Design System, it includes customizable light and dark themes, along with authentication and security modules. [Nebular on GitHub](https://github.com/akveo/nebular) ### CVAT Computer Vision Annotation Tool. Open source, 2019. I contributed to CVAT, an open-source platform for preparing image and video datasets for computer vision. It brings annotation tools, automated labeling and team review workflows together to help turn raw data into training datasets. [CVAT on GitHub](https://github.com/cvat-ai/cvat) [CVAT on NASA ADS](https://ui.adsabs.harvard.edu/abs/2020zndo...4009388S/abstract) ## Skills and Education - AI: OpenAI, Anthropic Claude, AI agents, tool calling, MCP, real-time voice agents, RAG, structured outputs, evals and prompt engineering, Claude Code and Codex plugins - Engineering: TypeScript, Node.js, NestJS, React, Next.js, Angular, Swift, SwiftUI, Ionic, React Native, PostgreSQL, Supabase, AWS, Cloudflare, Railway, Docker - Leadership: Engineering management, hiring, pre-sales and estimation, AI adoption in engineering teams - Belarusian State University, Computer Science - Languages: Belarusian (native), Russian (native), English (professional) ## Now - Building. Working AI prototypes for pre-sales, and an AI interview coach for iPhone on the side. - Running. Weekly AI meetups at Akveo, which I co-organize; 12+ sessions so far. - Writing. Building my site with AI agents, and how I estimate software projects. ## Links - [About](https://www.zankevich.com/about): experience, projects, results, contributions, training and the CV (Markdown: https://www.zankevich.com/about.md) - [Blog](https://www.zankevich.com/blog): posts on building AI features, AI-assisted development and leading engineering teams (RSS: https://www.zankevich.com/rss.xml) - [LinkedIn](https://www.linkedin.com/in/zankevich) - [X](https://x.com/ArtyomZankevich) - [GitHub](https://github.com/zankevich) - [Stack Overflow](https://stackoverflow.com/users/2208606/artyom-zankevich)