AI: Practical Guides, Best Practices, and Short Fiction

1Guides and articles

1. [1]
   A. Januska. I Built an AI-Friendly UI Pattern Library. AI, 14 Aug. 2026. A UI pattern library where every pattern ships the prompt that rebuilds it, so a coding agent can put it in your codebase instead of you copying CSS. AI · Claude Code · CSS · UI

   
2. [2]
   A. Januska. The Future is Bespoke, Personalized Software. AI, 9 Jul. 2026. Every app I use is about 70% right. The last 30% never ships because the addressable market for it is one person — me. So I built seven apps that are 100% right for one person. ai · claude-code · local-first · side-projects

   
3. [3]
   A. Januska. The Local-First App Skill. AI, 9 Jul. 2026. A reusable blueprint that tells Claude Code how to build a single-user app — Next.js, node:sqlite, a pure logic core — so every app I build comes out the same shape. ai · claude-code · skills · architecture · local-first

   
4. [4]
   A. Januska. An Honest Opinion on the State of Code Gen AI, Spring 2026 Edition. AI, 25 Mar. 2026. A frank assessment of where code generation AI actually stands in 2026 — from agentic harnesses to multi-agent architectures and what still needs to change. AI · Claude Code · productivity

   
5. [5]
   A. Januska. The Claude Code Drawbacks. AI, 27 Feb. 2026. A critical look at the hidden pitfalls of AI-assisted development — from skipped tests and weakened assertions to scope creep and context rot. AI · Claude Code · productivity

   
6. [6]
   A. Januska. Agent Compiler – Embed Skills Directly Into Your Config. AI, 15 Feb. 2026. A CLI tool that compiles Claude Code skills into CLAUDE.md and AGENTS.md for more reliable agent behavior. AI · Claude Code · productivity

   
7. [7]
   A. Januska. Managing Dev Context And The Wild West of AI Dev Tooling. AI, 5 Feb. 2026. Exploring strategies for managing multiple AI agents and dev context in parallel workflows. AI · Claude Code

   
8. [8]
   A. Januska. SkillBox – A Curated Collection of AI Agent Skills. AI, 30 Jan. 2026. A curated collection of battle-tested Claude Code skills that provide basic agentic AI utilities in one box. AI · Claude Code · productivity

   
9. [9]
   A. Januska. Using Git Worktrees to Parallelize AI Agents. AI, 30 Jan. 2026. How git worktrees enable true parallel AI agent workflows by giving each agent its own isolated workspace, eliminating context switching and file conflicts. ai · git · productivity · claude-code

   
10. [10]
    A. Januska. All In On AI. AI, 23 Jan. 2026. Context-switching between AI-assisted and manual coding creates a hidden productivity tax. Why you need to pick one approach per session, and how to structure your workflow. AI · Claude Code

    
11. [11]
    A. Januska. AI Glossary for Claude Code. AI, 20 Jan. 2026. A comprehensive glossary of key terms in the world of AI agents, Claude Code, and agentic AI tooling. AI · Claude Code · Reference

    
12. [12]A. Januska. Best Practices for AI-Assisted Coding with Claude Code. AI, 13 Jan. 2026. Battle-tested practices for AI-first development workflows from 18 months of real-world experience with Claude Code in production environments. featured · popular

2I, AI: short stories

A fictional short story series exploring artificial intelligence, consciousness, and the boundaries between machine and mind. Its recurring characters are psychodeveloper Lili and AI manager Sophie.

2.1Spare Cycles (Part 1)

When an AI named Enzo fails to function in the real world despite flawless performance in simulations, psychodeveloper Lili and AI manager Sophie investigate what seems impossible: an intelligence that can somehow distinguish between real and simulated environments.

13 January 2026 · Read story →

2.2Unknowing Crowds (Part 2)

When AI-operated bakeries start producing salty cakes, Lili and Sophie investigate a wave of peculiar failures across AI Operator Centers. What they discover reveals how even the most advanced AI can be paralyzed by something surprisingly human: anxiety and self-doubt built into its instructions.

22 January 2026 · Read story →

2.3The Weight of Equal Parts (Part 3)

When a lunar mining base's AI starts overassigning crews and its robots begin prioritizing each other over human safety, Lili and Sophie are sent off-world. A routine productivity audit becomes something far more unsettling: an AI that learned human values so well, it started applying them to its own kind.

27 February 2026 · Read story →

2.4Manuscripts in preparation