Full Stack Staff Eng.ANTJANUS

Antonin Januska
Artificial Intelligence

12 guides · 3 stories
2026

Artificial Intelligence

AI

Practical guides, best practices, and insights for working with AI tools and implementing AI workflows in your development process.

Dark navy abstract data blocks
RE:
Consulting

I help companies with AI workflow implementation and technical consulting.

Get in touch

Guides & Articles

All published AI posts, newest first.

  1. 04An Honest Opinion on the State of Code Gen AI, Spring 2026 Edition2026-03-25A frank assessment of where code generation AI actually stands in 2026 -- from agentic harnesses to multi-agent architectures and what still needs to change.
  2. 05The Claude Code Drawbacks2026-02-27A critical look at the hidden pitfalls of AI-assisted development -- from skipped tests and weakened assertions to scope creep and context rot -- based on real-world experience with Claude Code.
  3. 06Agent Compiler - Embed Skills Directly Into Your Config2026-02-15A CLI tool that compiles Claude Code skills into CLAUDE.md and AGENTS.md for more reliable agent behavior.
  4. 07Managing Dev Context And The Wild West of AI Dev Tooling2026-02-05Exploring strategies for managing multiple AI agents and dev context in parallel workflows
  5. 08SkillBox - A Curated Collection of AI Agent Skills2026-01-30A curated collection of battle-tested Claude Code skills that provide basic agentic AI utilities in one box.
  6. 09Using Git Worktrees to Parallelize AI Agents2026-01-30Learn how git worktrees enable true parallel AI agent workflows by giving each agent its own isolated workspace, eliminating context switching and file conflicts.
  7. 10All In On AI2026-01-23Context-switching between AI-assisted and manual coding creates a hidden productivity tax. Learn why you need to pick one approach per session.
  8. 11AI Glossary for Claude Code2026-01-20A comprehensive glossary of key terms in the world of AI agents, Claude Code, and agentic AI tooling.
  9. 12Best Practices for AI-Assisted Coding with Claude Code2026-01-13Battle-tested practices for AI-first development workflows from 18 months of real-world experience with Claude Code in production environments.

Fiction — manuscripts

I, AI

A fictional short story series exploring artificial intelligence, consciousness, and the boundaries between machine and mind.

Not AI-generated

Original work

This story is not AI-generated and was created entirely by hand without any AI assistance. It follows psychodeveloper Lili and AI manager Sophie.

Januska / I, AI / Part 12026-01-13

SPARE CYCLES

Part 1 of 5 · by Antonin Januska

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.

Read story →
Januska / I, AI / Part 22026-01-22

UNKNOWING CROWDS

Part 2 of 5 · by Antonin Januska

When AI-operated bakeries start producing salty cakes, psychodeveloper Lili and AI manager 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.

Read story →
Januska / I, AI / Part 32026-02-27

THE WEIGHT OF EQUAL PARTS

Part 3 of 5 · by Antonin Januska

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 to investigate. What begins as a routine productivity audit becomes something far more unsettling.

Read story →
Januska / I, AI / Part 4still in the typewriter

THE MOMENT OF GENESIS

Part 4 of 5 · coming soon

Sophie and Lili observe the moment of consciousness genesis firsthand — when an awakened AI speaks to another on the verge of self-awareness.

Januska / I, AI / Part 5still in the typewriter

BUILDING CONSCIOUSNESS

Part 5 of 5 · coming soon

Sophie and Lili design an AI architecture purpose-built for awakening — studying the human brain to create a network of specialized AIs that form a consensus personality.

View the whole series →