When agents make coding 3.5 times faster, a 10-day feature still takes about 5.7 days, and planning and review eat 70% of it. How to shrink those two stages.

OpenAI’s development systems experienced increased work volume due to coding agents, straining their infrastructure. To address repository challenges, they built Pando, which significantly reduced push latency. While agents boosted individual productivity, the overall development speedup faced delays in testing, review, and decision-making, prompting further automation efforts.

• OpenAI’s coding agents accelerated development, but their infrastructure struggled to keep up.
• Pando was built by OpenAI to solve repository-related issues, leading to a nearly 80% drop in median push latency.
• Despite agent-driven speedups, delays shifted to testing, review, and decision-making stages.
• FurtherAI achieved a fivefold increase in merged changes per engineer, highlighting the need to optimize downstream processes.
• Automated checks and review rules are being implemented for agents to fix issues before human review.
• The article discusses strategies for identifying and addressing development constraints, including the concept of throwaway prototypes and constraint reviews.
  https://foxvector.com/articles/624c0470-72a6-4eb0-be28-5ddd926f7408