Before clicking Find Patterns in Mezmo's parse processor, hand-pick or sanitize the sample lines: replace PII, tokens, and user-identifying fields with placeholders first. The generated regex is a starting point, so test and tweak it in the processor against real data before deploying the pipeline. Keep this feature out of production use until you have reviewed what the samples contain.

Context: Mezmo's parse processor docs carry a privacy warning on the AI pattern-matching feature. The AI generates a regex from a sample of your log data, but Mezmo sends those sample log lines to a third-party LLM over API. The docs explicitly say to scrub any sensitive or user-identifying data from the samples before using the feature.