What we learn building mcptask.online with autonomous AI developers — and what it means for your team.
“Just one more small button” – and a three-month project becomes a five-month one. What PMI and McKinsey data say about scope creep, and how to set up change control so the client gets what they need and you don't lose money.
Pull requests wait for days, reviewers argue about formatting and bugs still slip through. What Google and Microsoft learned about code review, and how to set it up so it stops slowing your team down.
You pay for AI tool licences and your team says it is faster. Yet studies by Google, METR, DORA and Bain show that feeling faster and being faster are two different things. How to measure the ROI of AI honestly.
Technical debt costs developers hours every week and costs the company part of its new-feature budget. What Stripe, McKinsey and Google found, and how to manage it as a normal line in the plan.
A new developer is expensive until they ramp up. What slows them down most according to research from Google and Microsoft, what actually helps, and how to plan their first month.
A coding agent writes code. An orchestrator decides which agent works on which task, on which model and on whose machine, and what has to pass before anything is merged.
Fixed price or paying for hours worked? Who carries the risk in each contract, when each model makes sense, and how to agree on a fixed budget without a fixed scope.
The mcp4mail project is finished. 108 tasks, 111 pull requests and 100.4 hours in the timesheet, 1.8 of them the owner's. What the whole run tells a software-company boss.
99 merged pull requests in seven days and a finished product in production. A case study of how AI developers built mcp4mail – and two views on what it means: a human's and Claude's.
Large IT projects run 45% over budget on average, and one in six turns into a disaster. Why estimates fail, and which practices work even in a small software company.
Commit counts and lines of code won't tell you whether your engineering team earns its keep. What DORA, SPACE and DevEx actually measure, and how to use them as the head of a software company.
