AI Development: The Engineer's Playbook
Stop using AI as autocomplete. Start using it to build systems. Here's the practical, no-shortcuts approach.
6 min read • 3 Apr 2026
AIagenticsoftware developmentcodingtestinginternal tools
Want a quick email when a new article is published? Subscribe
Stop using AI as autocomplete. Start using it to build systems. Here's the practical, no-shortcuts approach.
Your team's internal tools backlog is the perfect low-stakes proving ground for AI development. Here's why, and how to make it happen.
The cost of baking observability in from day one is close to zero. The cost of not having it can be measured in missed deadlines, lost revenue, and sleepless nights.
Much of software development is well understood. Smart teams, good communication, building the right things. But what about the parts that aren't in the online textbook?
A peer-reviewed study puts numbers to the AI coding debate. The results might surprise the sceptics.
Cutting through the noise on AI-assisted development, for people who need to make decisions about it.
When your tech team blames slow progress on 'context switching', they probably mean something else entirely.
A peek behind the curtain of PE/VC technical DD. What raises red flags, what impresses, and how to prepare.
Aviation has spent a century formalising how to handle human error. It is time software engineering caught up.
Most companies have spent 18 months playing with LLMs and have nothing to show for it. The problem isn't the technology.