Why ProfileScribe keeps fact extraction separate from claims
Abstracts
Abstracts
A recurring design choice in ProfileScribe is drawing a hard line between what a source actually says and what your profile eventually claims. The crawler agent prototype fetches approved public links and extracts timestamped facts before anything reaches the professional memory. Only after that does a separate step decide what is worth surfacing.
The reason is simple: a profile is credible when its claims can be traced back to evidence. Keeping extraction and presentation apart makes each step reviewable on its own terms. It is less about automation for its own sake and more about building knowledge you would be comfortable defending later.