When to Replace expense reporting With an Agent — and When Not To
Inside the quiet rewiring of code review at HubSpot.
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.
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.
Inside Spotify, the rollout looked less like a moonshot and more like a slow migration. A pilot, a champion, a quiet expansion, a budget line.
Eval harnesses, once an afterthought, are becoming the most important piece of code in many AI projects. HubSpot's team treats theirs the way an SRE team treats a runbook.
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.
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.
What Inflection 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.
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.
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.