Capital Allocators · Monday, September 14, 2026
Abby Barlow cautions that while AI tools are powerful, they are not infallible, especially when dealing with numbers and complex data. She emphasizes the need for thorough human review, comparing it to a junior analyst's work, and shares an anecdote about Claude double-counting commitments in a pacing model.
“It does make mistakes. Especially when you're dealing with numbers and complexity. It gets me to a solid first draft. I need to thoroughly scrub it. It's like a junior analyst would do.”
“You would never take something an analyst would give you the first time and be like, this is perfect. I'm showing it to the family. It was double counting some of our commitments in our pacing model. I was building. It's hard to catch that stuff.”
“I've gotten in a habit where I will ask it at the end of any deliverable. Go back to the beginning of this conversation and what we were trying to accomplish. Review the deliverable. Triple check all the numbers again. Find your own errors. It will be like, oh, I missed these three things.”