Running a Software Factory Efficiently at Uber Scale

Summary

Uber describes a Software Factory in which AI tools and managed agents support software development, with more than 70% of pull requests attributed to local or cloud agents and over 3,600 agent skills. From February to August 2026, weekly active users grew sevenfold and weekly agentic requests 9.4-fold, while holding a model constant showed cost per 1,000 requests down almost 34% and cost per session down 52% from its June peak. The framework organizes usage into four layers and decomposes session spend into adoption, engagement, input and output workload, token pricing, and related execution factors measured through portfolio, model, driver, and managed-agent outcome metrics. Its optimization program uses real-work benchmarks, Pareto model selection, cheaper subagents, prompt caching, graph-grounded context, batched tool calls, and session-level waste analysis to reduce zero-value token use while improving or maintaining quality.

Takeaways

1. 1

   From February to August 2026, weekly active users across Uber’s agentic offerings grew 7x and weekly agentic requests grew 9.4x, while total AI spend relatively stabilized after April.

2. 2

   With one model held constant from February to July, cost per 1,000 model requests fell almost 34% from its peak and cost per session fell 52% from its June peak.

3. 3

   uReview benchmarks real pull requests with known bugs and scores precision, recall, F1, cost per review, latency, timeouts, and noise to guide Pareto-efficient model selection.