Developer: My Elaborate AI Workflows Kept Failing — Just Focus on the Outputs

brandon_galang · x · 2026-11-17

Developer brannongalang agrees with thdxr's take that no one evangelizes their AI workflows — only outputs matter, since 99% of the magic comes from the model. He admits that over the past year he repeatedly fell into AI-psychosis-driven "workflow design" rabbit holes, and nearly all ended with him rejecting what he built in favor of simply checking whether he got the outputs he needed. LLM intelligence is too malleable and versatile to over-constrain your usage.

Original post →

More from coding & agent

coding & agent channel →