Écrits
Analyses, tutoriels et articles de fond sur les agents IA, l’automatisation et l’ingénierie produit.
July 30, 2026 · Business · 7 min de lecture
Nvidia has rallied nearly 40 tech giants — from Microsoft and IBM to SpaceX and Hugging Face — behind the Open Secure AI Alliance, a coalition building open-source tools to defend against AI-powered cyberattacks. Here's what it means, who's in, and the one name conspicuously missing.
Par Daniel Nikulshyn
July 27, 2026 · Security · 5 min de lecture
The Claude chats showing up in search results aren't a Claude problem. They're the web working exactly as designed — and most people building on it still don't get that.
Par Daniel Nikulshyn
July 19, 2026 · Team Culture · 10 min de lecture
Week 6 was supposed to be the close — exit interviews, a playbook, a quiet wind-down. The exit interviews said the quiet part out loud and the energy score told us why. So instead of ending it, we made the game a standing practice: a recurring room whose only job is to put the technical people together with no ticket attached.
Par Daniel Nikulshyn
June 5, 2026 · Automation · 5 min de lecture
Par Denys Hrynyk
May 27, 2026 · AI Engineering · 4 min de lecture
No-code combined with AI is fundamentally changing how software is built, allowing founders and creators to turn ideas into working products faster than ever before.
Par Yurii Kulakovskyi
May 26, 2026 · AI Engineering · 5 min de lecture
Most AI projects fail not because of technology, but because of strategy, data, and people. Here are six common mistakes companies make when adopting AI — and how to avoid them.
Par Oleh Kobrynovych
May 26, 2026 · AI Engineering · 2 min de lecture
AI is no longer a future trend — it's a practical tool helping teams automate repetitive tasks and focus on higher-value work.
Par Ihor Soloviov
May 21, 2026 · Team Culture · 3 min de lecture
A look into the history, symbolism, and cultural importance of the Ukrainian vyshyvanka — a timeless national symbol.
Par Anastasiia Nikulshyna
May 14, 2026 · AI Engineering · 8 min de lecture
Three weeks ago we converted every internal checklist we run more than once a month into a Claude Skill. Eleven went in. Six are still active, two got deprecated, three never shipped. Here's what we kept, what we killed, and the three-question filter we wish we'd used on day one.
Par Anderson da SIlva
May 14, 2026 · Team Culture · 7 min de lecture
Two more experiments delivered. The retrospective build caught the architectural decision the written post-mortem missed; the "explain it to me" challenge worked on three of five attempts, and the two that failed were the bigger lesson. Plus the second precondition for replicability we didn't see coming: a team willing to publish its own seams.
Par Daniel Nikulshyn
May 8, 2026 · Team Culture · 6 min de lecture
Two weeks, two experiments. Design and PM joined for a cross-role night that reshaped how we talk about UX, and a structured build challenge inside Minecraft surfaced architecture issues no sprint review ever did. Plus the harder question we're now sitting with: is any of this replicable?
Par Daniel Nikulshyn
May 8, 2026 · Automation · 2 min de lecture
I completed a full database coursework in just one evening using Claude - not by outsourcing the work, but by accelerating every step of the process. This is a story about how AI shifts your role from writing everything manually to effectively orchestrating the outcome.
Par Yurii Kulakovskyi
April 22, 2026 · Security · 4 min de lecture
What if your laptop had an AI living inside it, silently watching every process, file, and network request — stopping threats before they even become threats? The future of antivirus isn't signatures. It's intelligence.
Par Anderson da SIlva
April 19, 2026 · Team Culture · 2 min de lecture
What happens when a Minecraft server stops being just an after-hours hangout and quietly becomes part of how your team thinks? Here's week two of our Game-Test experiment.
Par Daniel Nikulshyn
April 3, 2026 · Team Culture · 2 min de lecture
We gave our developers a shared Minecraft server to unwind after work — and it accidentally became our most productive idea space. Here's what happened in week one of our Game-Test experiment.
Par Daniel Nikulshyn
March 26, 2026 · AI Engineering · 1 min de lecture
RAG (Retrieval-Augmented Generation) lets AI answer questions using your own data — not just general training. Learn how it works and why it's the most practical AI investment you can make right now.
Par Daniel Nikulshyn