Most Claude Code sessions go wrong in the first message.
Not because the model is weak, but because the starting prompt is vague: “fix this bug” or “add tests.” With nothing else to go on, the model starts editing before it has looked at the repository, and you spend the next ten...
A pipeline can return clean, well-formed, confident output and still be wrong, because it only saw part of the input.
I wrote up a postmortem on a contract-extraction tool built around that failure. A language model pulled renewal dates and notice periods from vendor contracts. A...
Most spreadsheet errors don’t come from bad formulas. They come from bad entries.
One person types “N/A”, another leaves the cell blank, a third writes “n/a “ with a trailing space. A date arrives as text. A region shows up as “North”, “north”, and “Norte”. Every formula...
Every template you borrow comes with decisions somebody else made for you.
Take an Excel template for tracking sales. A date format, a rule for how blanks are treated, a hidden column feeding a formula, a default filter that leaves out last year. None of it is necessarily wrong....