Agents Are Eating the Backend, One fine-tuned distillation at a Time
Inside the quiet rewiring of incident response at Klarna.
The interesting question is not whether Glean works. It does. The interesting question is what teams do with it once the novelty wears off.
The skeptical read is that we are watching a feature, not a platform. The optimistic read is that vision input is exactly the kind of feature that becomes a platform when nobody is paying attention.
Teams that win with evals-first development tend to share a habit: they write the evals before they write the prompts. Everything else follows from that.
Notion has been quietly running QBR prep through Cursor for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
The cost curve matters here. Grok 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.
What Mistral actually shipped with Llama 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.
Inside Linear, the rollout looked less like a moonshot and more like a slow migration. A pilot, a champion, a quiet expansion, a budget line.
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.