Stop building agents as a straight line: the 90-second test to cut fake dependencies

blaizedsouza · x · 2026-09-27

Reposting @imryven's argument: most agents are still orchestrated as a straight line ("do A, then B, then C"), even though half the steps don't actually depend on the previous one — so you pay for the wait on every run. He proposes a 90-second check before writing any orchestration code: walk the workflow step by step and ask at each seam whether the step truly needs the last one's output; keep real edges, cut fake waits.

Split what remains into a scaling pattern:

The quoted tweet links to his article "Graph Engineering: My System Checked Its Own Work. It Was Lying About It.", born from frustration with babysitting an agent that forgot what it was doing every twenty minutes.

Original post →

More from coding & agent

coding & agent channel →