Plan the day with tasks, habits, and ideas.
On the App Store · 1.0 Released 2026-11-05
View Case StudyAI, Data Science & Product
I’m Lukas. I build apps and tools that help people plan their day, compare costs, and work with AI. I shape the product, direct AI-assisted development, and check the result in use.
A Few Places to Start
Three projects that show how I approach product design, data modeling, and AI-assisted development.
Plan the day with tasks, habits, and ideas.
On the App Store · 1.0 Released 2026-11-05
View Case Study
Coordinate AI coding agents from brief to release.
Reusable Workflow
View Case StudyConsumer Apps · AI Tools · Knowledge & Productivity
I use AI agents for implementation and review. I’m responsible for the product direction, design choices, and release decisions.
Start with the person using the product and the decision they need to make. Identify the assumptions, data limits, and smallest useful workflow.
Keep product rules separate from the interface and services. Record trade-offs, protect saved work, and reuse code when the same need appears across apps.
Check the result through tests, independent review, and the installed or deployed app. In Car Shopping, review caught an unsafe URL import; I removed it and kept a regression test.
I connect product decisions with data analysis and practical software delivery.
The case studies show how I apply these skills, including the checks that caught problems and the limits of each result.
Earlier work in machine learning, data analysis, and AI applications.
Experiments in machine learning and early AI applications.
ML and reinforcement-learning experiments (a DQN Lunar Lander, a config-driven ML pipeline, an agent chat app) built with an AI coding agent.
Five Python mini-projects from an AI-builder course: crypto price plots, a CVPR paper scraper, GUI automation, image analysis.
Early-2023 Streamlit experiment: ChatGPT answers grounded in Google search results, plus a scheduled news-summary emailer.
Python classes and a notebook that model multi-leg option strategies and plot their payoff curves.
Notebook projects in predictive modeling, clustering, and text analysis.
Loan-default classifier on about 890K Lending Club records: cleaning, feature selection, an sklearn and XGBoost pipeline. Reworked in 2023.
Clustering and LDA topic modeling of about 10K Amazon Echo reviews to explore themes in positive and negative experiences.
Airbnb listing price regression plus topic modeling of guest reviews.
Scraped RateMyProfessors for three universities and fit a regression model to predict professor ratings.
Continue the Conversation
I’m interested in opportunities across AI, data science, and product development. If the work here is relevant to your team, I’d be glad to discuss the problems you’re solving.