IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
878 articles
04 May 2026 · 12 min read
agentic coding
From vibe coding to software craftsmanship. 84% of developers use AI tools, but only 29% trust the output. Here is the maturity model that separates the amateurs from the engineers.
Read more03 May 2026 · 7 min read
AI coding
Vibe coding hit $4.7B in 2025. AI code has 2.74x more security vulnerabilities. 95% of AI pilots fail to create ROI. Here is the real story behind the hype -- and why founders need to be careful.
Read more30 Apr 2026 · 8 min read
ai
How a non-technical business owner went from painful outsourcing cycles to building products himself with Claude, Gemini, Codex, and Google Stitch. Real workflow, real tools, real numbers.
Read more28 Apr 2026 · 10 min read
ai
A deep dive into building a local LLM API server on an RTX 3060. Ollama + FastAPI + Cloudflare Tunnel. 6 layers of security, real benchmarks, and hard-won lessons.
Read more21 Apr 2026 · 9 min read
agentic engineering
One year after Andrej Karpathy coined 'vibe coding', the industry is moving on. Discover why vibe coding fails at scale — context collapse, cognitive debt, zero system design — and how agentic engineering is emerging as the professional discipline for AI-first software development.
Read more20 Apr 2026 · 14 min read
ai
Part 11 of 12 — Build a real-time Streamlit dashboard: Kanban board, agent status, cost tracking, and human checkpoint approval.
Read more20 Apr 2026 · 17 min read
ai
Part 12 of 12 — The finale. Optimize costs, match models to agents, calculate ROI, and make your AI team production-ready.
Read more20 Apr 2026 · 13 min read
ai
Part 4 of 12 — Build the foundation: BaseAgent class, TeamState, agent config YAML, SQLite memory store, and tool registry.
Read more20 Apr 2026 · 42 min read
ai
Part 5 of 12 — Build the Product Owner and Business Analyst agents. The PO clarifies requirements and defines scope; the BA breaks them into actionable user stories with acceptance criteria. Full implementation with prompts and output schemas.
Read more
