Tool Use Is the New Reasoning: Notes from RAG-as-a-service
Notes from the teams shipping memory to real users.
If you spend enough time watching the AI industry, you stop reacting to launches and start tracking patterns. Tool Use Is the New Reasoning is one of those patterns.
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.
The skeptical read is that we are watching a feature, not a platform. The optimistic read is that structured outputs is exactly the kind of feature that becomes a platform when nobody is paying attention.
Linear has been quietly running onboarding through Zed for months. The results are unglamorous and, for that reason, more interesting than another benchmark chart.
Inside Databricks, 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.
None of this guarantees a clean story. Meta FAIR 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.