Scaling Laws After Llama 4: A Field Report
A field report on tool-first agents and what it changes for sales teams.
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.
Inside Booking.com, the rollout looked less like a moonshot and more like a slow migration. A pilot, a champion, a quiet expansion, a budget line.
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.
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.
Eval harnesses, once an afterthought, are becoming the most important piece of code in many AI projects. Booking.com's team treats theirs the way an SRE team treats a runbook.
What Google DeepMind actually shipped with Claude 4.5 Sonnet 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.
None of this guarantees a clean story. Cohere 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.