MK Comment Signal
Turns thousands of open-text engagement-survey comments into ranked themes with real verbatim evidence — PII removed, ready for a leadership deck.
The story, in brief.
Open-text survey comments are the richest — and most unread — part of an engagement survey, because reading and coding thousands of them by hand isn’t realistic. MK Comment Signal turns them into ranked themes with real verbatim evidence, PII removed, ready to inform an organizational decision.
How it’s built.
Upload the Perceptyx survey-comment PDF; a topic flow extracts the text for four survey questions; a series of analysis steps identify 4–5 recurring themes per question ranked by comment frequency, each backed by at least 12 verbatim quotes — with names, emails, and IDs auto-redacted. An optional Power Automate flow exports a formatted Word document to OneDrive.
What AI actually does here.
Reading the unreadable
Coding thousands of open-text responses by hand isn’t realistic for a People team — the agent reads the whole set and returns ranked themes with evidence, turning volume into insight.
Verifiable, not vibes
Each theme is backed by at least twelve real quotes ordered by frequency, so the finding can be checked against the source rather than trusted blind.
Privacy as a feature
Redaction is built into the pipeline, making it safe to analyze and circulate sensitive feedback — the guardrail that lets the analysis happen at all.