article
From Vibes to Durable Context
AI can speed up implementation, but it does not remove the need for good engineering. This article looks at how planning, human judgment, useful documentation, and a well-structured codebase can help coding agents make better decisions with less guesswork.
·4 min readarticle
Where AI Actually Helps Quality Engineering
AI-assisted QA is not just about generating tests faster. By carrying product context through planning, development, review and release, AI can shorten feedback loops, surface risks earlier and help teams make better decisions, provided its output is supported by clear specifications, guardrails and human judgement.
·3 min read
More posts from other Thinkmill voices
Your agent believes that docs folder
The agent trusted a committed docs folder of generated artefacts over my instructions. I deleted the lot and lost nothing.
·8 min readAre your AI agents making progress or producing work?
We shipped a working MVP for the Tech Council of Australia in two weeks using an agentic development workflow. Along the way, we learned how easily agents can produce convincing work without moving a product forward, and why engineers still need to decide what progress looks like.
·5 min readWhat AI use looks like in five enterprise design teams
Listening to design teams at Stripe, Shopify, Ramp, Atlassian, and Intercom, three ingredients become clear: a place to prototype, good context, and someone helping people put both to use.
·9 min read
Want to keep the conversation going?