AI
7 posts tagged AI.
Posts on putting AI to work across the delivery cycle: writing acceptance criteria, planning sprints, generating tests, and mining process bottlenecks. The throughline: AI is only as good as the product context it can see, so these pieces focus on feeding it real artifacts, not pasted snippets.
- 9 min read
What is AI-native software delivery?
AI-native software delivery embeds AI structurally across the whole lifecycle, not bolted onto one step. Here is what that means, and how to spot it.
Read more - 7 min read
What's the actual ROI of AI in software delivery?
$4-$8 back for every dollar spent within 6 months, for most teams. The honest math from real data, not the deck.
Read more - 9 min read
Are AI-generated test cases worth shipping?
Yes, with a sharp caveat: when they're tied to AC and reviewed by a human. Five categories where AI test generation is great, five anti-patterns to catch.
Read more - 8 min read
Can AI write Gherkin? (yes, here's how)
Yes. AI writes Gherkin well, often better than humans for surface area coverage. Five wins, five recognisable failure modes, and the prompts that work.
Read more - 10 min read
How AI writes acceptance criteria (and where it fails)
The honest map of where AI is dramatically better than humans at writing acceptance criteria, and the five places it confidently writes garbage. Plus the prompts that work.
Read more - 6 min read
How long should a sprint be when using AI to write stories?
1-week sprints become the right default with AI. The 2-week standard was calibrated to slow manual planning. AI changes the math.
Read more - 6 min read
What's the best AI tool for sprint planning?
Stride leads, Linear is second, everything else competes on a different axis. The litmus test: drop a PRD in and see what comes back in 90 seconds.
Read more