Durable Execution
-
The Agent Checked Its Own Work and Called It Done
Six preprints from October and November measured agent reliability instead of asserting it. Chained coding tasks drop from 95% completion to 51%, 11.5% of tool calls return success without doing the work, and swapping durable-execution hosts changed nothing.
-
Single-Prompt AI Hit Its Ceiling — the Next Gap Is Durable Execution
Andrew Ng's 2024 numbers made the empirical case that workflows beat models. By 2026 the missing layer is no longer the framework but the runtime: durable execution and durable memory. A single prompt has no state to lose; an agent does.