We released Search as Code (SaC) in June, achieving state-of-the-art performance on wide and deep research.
This week, we’re rolling out optimizations to SaC that further improve performance while cutting cost per task by nearly 10%.
How an SDK is shaped determines how well models can use it.
We’ve rolled out two batches of Search SDK updates within Computer, raising execution reliability from 81.9% to 92.6%.
More reliable action execution enables more capable orchestration.
These improvements show up across a wide range of real-world user workflows.
In Computer, SaC optimizations delivered higher user satisfaction at an 8% lower per-task cost.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Reshaping the search SDK the model calls lifted action execution reliability from 81.9% to 92.6% and cut per-task cost by roughly 8-10%, evidence that tool interface design is a first-class lever on AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → reliability.
