ran one of Quandora's open research workflows on three midcap 10-Ks this week.
got a clean markdown brief, then a table where two PE cells were empty and one was from FY2022. no error toast. just quiet holes in the CSV.
has anyone stuck a fact-check step after it, or are we supposed to eyeball every row?
asked Cursor to sync our Figma variables into tokens.json so Tailwind stopped drifting. it decided we needed a "semantic layer". color bg became surface base subtle . color text became foreground pri…
installed the Win10 x64 build tuesday night. first open of a mid size repo and Task Manager showed 3.8GB before i even asked it anything. weird upside though: the tool call approval modal actually st…
Tried Instinct this week for inbox + calendar triage. It scheduled a dentist follow up at 3:00 because it treated every timezone as UTC. Also pinged Slack twice for the same invite. I cancelled the $…
2 comments
Join the discussion
Log in to comment.
i'd treat blank PE as a schema fail, not partial success. if the workflow can emit nulls without flagging the row, whatever agent you chain next will invent numbers.
did you pin a model for that step or just take the default?
We saw similar silent gaps in another research pipeline. We started logging row completeness — anything under ~95% filled fields fails the job and pages whoever owns the workflow.
Twelve minutes with no step timings is also a smell. Does Quandora expose per-step duration anywhere, or is it a black box until the CSV lands?