I delivered a playable version of Glyphverse Zero as a solo developer in about a weekend using AI-first development, excluding marketing and distribution integrations. It is an indie incremental idle sci-fi game that turns camera input into ASCII glyphs and connects that visual system to an upgrade economy.
I am pleased to announce the official 2026 English edition of my doctoral dissertation, Predicting the Success of Technology Startups: Models, Empirical Evidence, and Software Tools.
This 187-page work brings together a methodology for predicting startup success, theoretical and empirically tested models, evidence from the Bulgarian entrepreneurial ecosystem, and the I3SP software tool that implements the approach. The study includes qualitative research and quantitative analysis of data from 136 companies, factor analysis, and classification models developed with IBM SPSS Modeler and Weka.
The underlying research was conducted and submitted in Bulgarian in 2015. This English edition presents the original work to an international audience; it is not a new study undertaken in 2026. The translation was prepared with AI assistance and reviewed and edited by me.
Download the official English edition (PDF, 45 MB).
Read the original Bulgarian publication and download the Bulgarian paper.
1. What I Learned About Trust After Becoming a Team Lead at Amusnet
Trust used to be something I expected people to earn but becoming a Team Lead at Amusnet changed that. I learned that trust isn’t a prize you hand out after people prove themselves – it’s the foundation you lay down on day one. If I want others to give their best, I have to trust them first, not because they’ve earned it yet, but because I believe in their potential. To me, trust is about vulnerability. It’s when I’m able to say “I don’t know, let’s figure it out together” that true collaboration begins. This mindset helped create a culture of psychological safety, where people can grow, take initiative, and be honest.
Can you share a bit about your topic, “Architecting iGaming Innovation: Internal Tools and Components”?
Boyan: I showcased the Asset Debug Tool, a solution that streamlines collaboration between animators and developers for spine-based games, enabling faster and more efficient development.
What’s the biggest takeaway you hope the audience gained from your session?
Boyan: I wanted attendees to see how innovative tools and architectures like ours can elevate iGaming development and inspire them to push boundaries in their fields.
Abstract: BlockChi creates an easy way of storing and retrieving data on the blockchain. It is a technology that solves some of the current limitations of blockchain storage and public blockchain networks that have transaction payload support. It allows parties to author, publish, extend and access data records in a decentralized, immutable and secure manner, supports complex data types, such as structured data and media, supports metadata to allow anonymously, identified or trusted publishing. BlockChi format is compatible with various blockchain networks. Data is presented as a JSON object, encoded in hexadecimal format and contained in the payload of blockchain transaction(s). There is an Ethereum implementation – BlockChiEth, which is a JavaScript class that allows frontend and backend applications (DAPPs) to interact with Ethereum blockchain.
Cryptocurrency All-in-One is a project of mine that I started in 2016. My idea back then was to help make cryptocurrencies more popular. I liked the whole idea of decentralized currencies and blockchain technology. But back then cryptocurrencies lacked the high-level tools for developers to integrate them easily into real-life projects. I decided to help web developers and start-up owners to adopt Bitcoin, Ethereum, and other cryptocurrencies by providing a free and simple-to-use WordPress plugin and that was how Cryptocurrency All-in-One came into existence. I submitted the first version to the WordPress.org repository in August 2016.
Abstract: For achieving an optimal esthetic result from a dental treatment we need to create a suitable smile design that creates a perception which fulfills the esthetic expectations of the patient. It is also important that the teeth proportions to be correctly diagnosed and designed before an irreversible restorative dental procedure to be done.
Excellent quality digital smile design software products exist on the market. However these solutions do not apply in its fullness the visagism concept which produces a smile design in relation to the facial type and personality of the patient which is perceived as more harmonious. The visagism concept has been recently applied in the dental software “VisagiSMile” which helps clinicians to personalize and improve smile designs.
VisagiSMile is a software that automates the process of creating personalized digital smile design. VisagiSMile is a multiplatform web application for aesthetic dentistry which does not require installation, but only a simple registration process to get started. All cases and data are stored on a server to allow dentists to work on different devices and platforms – computers, tablets and smartphones. The research on the visagism concept is an ongoing process which constantly changes the requirements for the software. With the ongoing development of the software as an agile web application new versions are released every few weeks. Future plans include improvement of the accuracy of algorithms and of the teeth designs. Together with the product development, VisagiSMile’s user base also grows with over 1000 currently registered dentists.
Abstract: The visagism concept in dentistry tries to achieve the most appropriate smile design for every individual patient. The design is based on facial analysis, the patient’s personality and their preferences, and is calculated and visualized as a teeth configuration. The paper presents VisagiSMile — aesthetic dentistry software which automates the theory of dental visagism. The goal of VisagiSMile is to automate this process of creating aesthetic cases and to eliminate the human factor from the analysis. Based on innovative data mining approach, the software learns to classify patients’ faces correctly and then makes the necessary calculations to produce harmonious teeth configuration which can be further adjusted.
Резюме: Методиката и моделите за предсказване на успеха на стартиращи компании, представени в статията, са резултат от тригодишно проучване на предприемаческата екосистема в България. Предложени са модел на процеса на създаване на компания и модел за предсказване на успеха, които са базирани на проведено качествено изследване. Проведено е и количествено изследване върху набор от данни за 136 компании. Чрез прилагането на метода факторен анализ, са потвърдени предложените в модела категории и подкатегории фактори, определящи успеха на стартиращите компании. С помощта на софтуерните продукти за извличане на знания от данни – IBM SPSS Modeler и Weka са синтезирани класификационни модели, които с висока точност предсказват успеха. Получените резултати са приложени и внедрени в I3SP – информационна система за предсказване на успеха на стартиращи компании.
Abstract: The methodology and the success prediction models presented in the articles are results from three years of research of the entrepreneurial ecosystem in Bulgaria. A model of the process of creating a company and a success prediction model have been proposed, based on the conducted qualitative research. A qualitative research on a dataset for 136 companies has been conducted. The method factor analysis confirms the proposed categories and subcategories of factors in the model, which determine the success of start-ups. Classification models, which predict the success of start-ups with high accuracy, have been synthesized by applying the data mining software products IBM SPSS Modeler and Weka. The results are applied and implemented in I3SP – Information System for Start-ups Success Prediction.
Текстът на дисертацията е организиран в 5 глави, списък на фигурите, списък на таблиците, основни използвани термини, заключение, библиография и 3 приложения.