| Feels like we’re all shipping faster, but the old “just write more tests” advice isn’t keeping up. Teams are smaller, release cycles are tighter, and AI is sneaking into a lot of workflows. I’m curious what people here are actually relying on these days to keep things from breaking: - What layers are in your stack? (types/linters, unit, contract, integration, E2E, monitoring, flags, SLOs, etc.) - Is AI playing a real role yet for you? test gen, self-healing, triage, anomaly detection? - Anything you dropped recently because it wasn’t worth the effort? (flaky UI tests, snapshot tests, staging envs…) - For smaller teams, do you still bother with classic QA, or do you lean more on flags/observability/canaries? - Anyone tried managed or AI-assisted QA instead of DIY? Curious if it actually worked, esp. around trust/cost/lock-in. - How do you measure “confidence to release” beyond code coverage? Would love to hear quick snapshots like:
- team size / release cadence - stack (web, mobile, regulated or not) - pre-merge checks - post-deploy safeguards - tools you kept vs abandoned - biggest source of flakiness right now - what you’d do differently if starting today Looking for real, on-the-ground stories from folks shipping in 2025. What’s working for you? |