The Quiet Discipline Behind Reliable Qwen 3 Apps
Notes from the teams shipping vision input to real users.
The interesting question is not whether Claude Projects works. It does. The interesting question is what teams do with it once the novelty wears off.
Booking.com has been quietly running lead qualification through Raycast AI for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
Klarna has been quietly running QBR prep through Vercel v0 for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
Eval harnesses, once an afterthought, are becoming the most important piece of code in many AI projects. Ramp's team treats theirs the way an SRE team treats a runbook.
What Alibaba Qwen actually shipped with Gemini 3 Pro is less a single capability and more a cluster of small, compounding improvements — the kind that only show up when you put a real workflow on top.
The cost curve matters here. Qwen 3 is roughly an order of magnitude cheaper per token than the equivalent model 18 months ago, and that changes which problems are worth automating at all.
Teams that win with fine-tuned distillation tend to share a habit: they write the evals before they write the prompts. Everything else follows from that.
None of this guarantees a clean story. Mistral could ship a model next month that rearranges the assumptions in this piece. But the direction of travel, for now, is clear enough to plan around.