Think Different by Jakub Jirák - Blog
-
Google Gemini: Separating research (AI Studio) from execution (Code Assist) on purpose
A field-tested take on separating research (AI Studio) from execution (Code Assist) on purpose with Google Gemini: what it rewards, where it breaks, and how to keep the workflow honest.
-
Why Fewer Tools Is Often More: Minimalism in the QA Toolchain
Discover why reducing your QA toolchain often leads to better test coverage, faster pipelines, and happier teams. A practical guide to tool minimalism in.
-
Monthly Retrospective: What April Taught Me About Technology and Productivity
A personal retrospective on April 2026 covering technology experiments, productivity insights, and honest reflections on what worked and what didn't in.
-
ChatGPT Codex: Replaying failed tasks with tighter prompts instead of starting over
A field-tested take on replaying failed tasks with tighter prompts instead of starting over with ChatGPT Codex: what it rewards, where it breaks, and how to keep the workflow honest.
-
Why Process Matters More Than Technology
Discover why process beats technology every time when building successful software teams. Learn practical frameworks for improving workflows without.
-
Claude Code: Running Claude Code headlessly in CI as a structured reviewer
A field-tested take on running Claude Code headlessly in CI as a structured reviewer with Claude Code: what it rewards, where it breaks, and how to keep the workflow honest.
-
Personal Automation Pipeline: From Idea to Finished System
Master the art of personal automation with this comprehensive guide. Learn how to identify automation opportunities, build reliable systems, and maintain.
-
GitHub Copilot: Wiring MCP servers into Copilot to give it domain-specific tools
A field-tested take on wiring MCP servers into Copilot to give it domain-specific tools with GitHub Copilot: what it rewards, where it breaks, and how to keep the workflow honest.
-
What Being a 10x Developer Actually Means
Discover what being a 10x developer actually means beyond the myth and controversy. This honest examination reveals how high-impact engineers create.
-
Local LLMs with Ollama: Quantisation choices that actually matter for code
A field-tested take on quantisation choices that actually matter for code with Local LLMs with Ollama: what it rewards, where it breaks, and how to keep the workflow honest.
-
API Design from the User's Perspective, Not the Architect's
Learn to design APIs from the user's perspective rather than the architect's. This practical guide covers developer experience, intuitive naming, error.