AI in practice
Uses, limits and integration of AI in software development.
AI detection meets the reality of how we work
A detector estimates resemblance; provenance signals tell us something about a file's history. What can either reveal about work made with AI?
Vibe Coding or Orchestration: What AI Really Changes About Being a Developer
An agent can write most of the code. The real question is who defines the constraints, checks the result and can take back control.
When the app joins the conversation: what MCP changes about the experience
MotorTrack can be used from ChatGPT without learning a new interface. Usage becomes natural after an initial setup that still requires some hand-holding.
From AI assistant to AI agent: when conversation becomes action
AI assistant, tool-using assistant, AI agent: three levels we keep conflating. The difference isn't the number of tools used, but who decides the steps and drives their sequence.
AI Is Reshaping Our Jobs Faster Than the Market Can Name Them
AI Engineer, AI Integrator, AI Consultant... Job titles keep multiplying while the boundaries between roles blur. Can the labor market keep up with the pace of change AI is imposing?
When a Bug Resists AI Agents
A firsthand account of an integration issue where more context did not help AI agents converge on the right solution.
Why does using AI still feel uncomfortable?
A friend spotted phrasing typical of generative AI in one of my texts. My reaction, for a brief moment, says a lot about how we still view people who use these tools.
From "snail mail" to "snail brain"
The shift from paper mail to email comes back to me with the arrival of AI. From snail mail to snail brain, what does a new reference point reveal?
Developers barely type the code anymore — but they still own the outcome
AI has erased the technical friction. The difficulty no longer lives in the code but in the clarity of intent — and the responsibility has remained entirely yours.
MCP + Sentry & GlitchTip: giving context to your AI agents
A hands-on account of integrating Sentry and GlitchTip MCP servers into an AI workflow — why, how, and what you learn along the way.
The LLM, a Mirror of Our Identity
Switching LLMs made me realize I wasn't just changing tools. That experience led me to reflect on how artificial intelligence gradually becomes an extension of the way we think.