Uber and Microsoft both capped per-engineer AI spending in 2026 after burning through annual budgets in months. A smaller number doesn't stop one run from looping for hours. An execution pattern borrowed from site reliability engineering does.
Tool definitions load into context before an agent does anything. Code execution and progressive disclosure are how teams are getting that budget back.
Middle management is flattening industry-wide. What survives of engineering management is splitting into two tracks that need almost opposite skills.
Prompts drift. A versioned spec is how teams are catching it before it ships.
A framework for deciding how many agents one engineer can actually run at once.
A framework for staff engineers directing several agents at once, not just reviewing what one of them wrote.
A framework for staff engineers reviewing pull requests an agent wrote.