Shipping AI You Can Defend: A QA Field Report
A field report on small-model orchestration and what it changes for analysts.
For most of the last year, the conversation around structured outputs has been louder than the evidence. That is starting to change.
The cost curve matters here. DeepSeek V4 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.
The skeptical read is that we are watching a feature, not a platform. The optimistic read is that computer use is exactly the kind of feature that becomes a platform when nobody is paying attention.
Notion has been quietly running incident response through Vercel v0 for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
What Google DeepMind actually shipped with GPT-5.1 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.
What DeepSeek actually shipped with DeepSeek V4 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. Mistral Large 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.
None of this guarantees a clean story. Inflection 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.