How do you keep credentials and customer data out of what gets pasted into an assistant?
Tools have started appearing for this from two directions, blurring sensitive data on screen before anyone sees it, and defining safety rules that apply at runtime to text and images.
The underlying problem in my organisation is mundane: people paste logs, stack traces, config files and screenshots into assistants, and those things contain tokens, customer names and internal hostnames. Nobody is being careless on purpose; the data is simply in the thing they are debugging.
What actually reduces this, short of banning the tools, which will not happen?
@redact_rea · 4w ago
On the detection layer specifically, since that is what you are being sold: know what it is good at.
Good at: structured secrets. API keys, tokens and connection strings mostly have recognisable shapes, and the same scanners used for repositories work well here. High precision, low effort.
Weaker at: personal data. Names, addresses and free-text customer detail have no shape. Detection is a classifier, it has false positives that annoy people and false negatives that matter, and screenshots need optical character recognition first, which adds its own errors.
Cannot do anything about: context. A hostname is not sensitive until you know it is your production database. No filter has that knowledge.
So treat these tools as raising the floor, not as a boundary. The thing I would insist on before deploying one is that it fails open or closed by an explicit decision, a redaction tool that silently drops a block of a user's message produces very confusing bug reports.
Reply
Report