I like difficult problems — not because they're easy to explain, but because they're interesting to solve.
More: Machine Learning Lab · All repositories
01 UNDERSTAND Start with the problem, not the framework.
02 DESIGN Think about boundaries, trade-offs and failure modes.
03 BUILD Make it real.
04 BREAK Test the things that shouldn't fail.
05 DOCUMENT If a decision matters, write down why. (26 ADRs and counting.)
◉ Finishing SecureSync toward v1.0
◉ NetScope — turning the MVP into a real diagnostic platform
◉ NexusAgent — tool selection and memory
◉ Football Battle Arena — phase by phase
| Telegram bots | Shops, subscriptions, games, moderation, AI assistants — designed, deployed and maintained. |
| Web applications | Django / Flask / Next.js backends and frontends, from idea to production. |
| Systems & security tooling | Networking tools, honeypots, encrypted communication, automation. |
| AI integration | Adding ML and LLM features to existing products. |
