Why Claude 4.5 Sonnet Feels Different, Even When the Numbers Don't
Inside the quiet rewiring of customer support at Klarna.
There is a version of this story that is mostly hype. There is another version, the one we are interested in, that is mostly engineering.
What Google DeepMind actually shipped with Grok 4 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.
Linear has been quietly running contract review through Perplexity for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
Teams that win with tool-first agents tend to share a habit: they write the evals before they write the prompts. Everything else follows from that.
The cost curve matters here. Phi-4 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.
Atlassian has been quietly running customer support through Claude Projects for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
None of this guarantees a clean story. xAI 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.