I'm Darius. I like turning ideas into products people can actually use. Everything below is live right now — feel free to click in and look around.
AI-powered personal cloud storage — upload, understand and manage all your files.
AI mock interviews and resume analysis with real, role-specific feedback.
An AI creator cockpit — create once, grow everywhere.
More projects on the way — always building.
Open-source projects I follow and recommend — star counts live from GitHub.
Thai & Lao text-to-speech balancing pronunciation accuracy with natural prosody, built on CosyVoice2.
AI video repurposing workflow — auto translation, editing, highlight extraction, comment analysis and remixing.
This article presents a practitioner framework for engineering leaders on how to prioritize AI features in quarterly roadmaps. It argues that sequencing, evaluation strategy, and shared infrastructure matter more than raw capability. Key takeaways: define evaluation criteria before roadmap entry, surface architectural dependencies as first-class items, and use a hybrid scoring model.
Read →
A practical, step-by-step guide on building executable AI product roadmaps for startup CTOs, PMs, and engineering leaders. It argues that roadmap failure stems from poor translation between vision and technical constraints — not lack of ambition. Key takeaways: sequence work by data dependencies, define a minimal intelligent system, build evaluation infrastructure early, and use time-boxed experiments.
Read →
A comprehensive 2026 guide to production-ready full-stack AI tech stacks, targeting founders, CTOs, and engineering leads. Argues that architecture choices — observability, RAG retrieval, streaming UX — matter more than model selection. Key takeaway: use abstracted LLM layers, LangChain for complex workflows, pgvector or Pinecone for retrieval, and ship a thin vertical slice early.
Read →No posts yet
I believe AI shouldn't stay stuck in demos and wow-moments — it should grow into real products and run in real situations. Every project above is a test of that idea: turning intelligence into something useful every day, not a one-off trick.
So they share one thing: AI is a native capability, not a bolt-on button — and all of them are deployed on real domains, running right now. Let AI understand your files, give interviews honest feedback, let creation grow in one place and distribute everywhere. Being genuinely useful is the real bar for AI.