Agent Graph Engineering, Part 5: How to Build Safer AI Agents With Structured Errors and Guardrails

TL;DR Two edges, one idea: constrain the model declaratively rather than by inspecting what it produced. A tool is a function plus metadata, and it signals failure by raising a structured error, never by returning a string the model has to interpret. An action that cannot be undone needs at-most-once execution, because a crash inside … Read more

Please stop asking me when the AI bubble will pop

Emmanuel Roman, chief executive officer of Pacific Investment Management Co. (Pimco), during the Global Financial Leaders’ Investment Summit in Hong Kong, China, on Tuesday, Nov. 3, 2026. | Bloomberg via Getty Images People, including on this staff, keep asking me with varying degrees of excitement or trepidation when the AI bubble will burst. I’ll tell … Read more