Marcus Chen

Great update!! Can't wait to use this skill and manage my blog from codex.

The vendor question at the end is the useful bit. I asked our current tool's support team almost exactly this last quarter and got a healing percentage back, which tells you something. One thing the post doesn't cover: what does a redesign actually cost under intent re-resolution? If 200 cached steps invalidate at once, that's 200 AI resolutions in one run. Is that minutes or hours, and who pays for the tokens?

Managed QA definition has drastically changed in 2026. Traditional agencies aren't relevant anymore.

Good one Sandeep.

Refreshing to see a founder admit where his own tool falls short. The columns thing is so real. We trialed two of these last year and both nailed the beams in the demo, then choked the second we threw a job at them with no column schedule. Bookmarking this.

The part that trips up most teams I talk to is the eval-style testing section. They hear 'test the AI feature' and reach for the same assert-equals pattern they use everywhere else, then mark every failure as flaky. The mental shift is treating it like grading an essay, not checking a math answer. You are scoring properties against a rubric, not matching a string. Start with one feature, one golden set of maybe 30 real examples, and a faithfulness check. That alone catches more than most full suites do today.

Great list!!

Interesting how the AI testing qa space is chaging in 2026…

nice writeup!

Nice write up Fazle