workingsoftware.dev

Every software company wants to push its teams toward agentic AI, hoping to get faster.

Table of Contents Motivation The paradox: falling prices, rising bills Why build cost decouples from developer time "A developer costs $12,000 - tokens are noise" Build vs.

Table of Contents Motivation What exactly is a skill?

For most of computing history, programming has been an act of translation: understand the problem, design a solution, then render it in syntax a machine can execute.

Every week, AI coding tools introduce new features, rename old ones, and invent fresh terminology for concepts that often already exist elsewhere.

Recently, I needed to import issues from Atlassian Jira into Claude Code.

Let me start with a short story.

Supporting a new initiative as a Software Architect involves more than just selecting technology – it requires establishing clarity, boundaries, and direction in an environment full of uncertainty.

As a CTO, Tech Lead or similar technology leader, you often guide your organization through transformation to outperform your market.

What would YOU do as a Software Architect in the following scenario❓ Comment directly under the post and help me find the right approach here.

Software architecture is the basis for the successful development of software products.

Recently, I spoke on the Heise SoftwareArchitekTOUR Podcast with Ole Wendland from INNOQ about the MCP in practice and what software architects need to know about the Model Context Protocol.

Recently, a client asked me to automatically retrieve the latest product prices from Google for a specific item - for example: Segway-Ninebot F3 Pro D 500W.

I’ve been experimenting a lot with LLMs recently - and I keep coming up against the same hurdle: How can you connect your local AI with tools and data from the real world?

How can AI be used to create a dynamic real-time experience - without hard-coding the results?