Tool Gate · How it works
How the PII Detection for Structured Data gate works
How PII Detection for Structured Data grades a dataset: each column is HANDLED, MASK FIRST, or EXPOSED, and one regulated column left exposed trips the gate to HOLD — which is why an 83%-handled dataset with an open SSN column still can't be used.
How the gate works
This tool grades each column of a structured dataset for exposed PII. Each of 8 signals is scored 0–2 from your own evidence; the verdict is the weakest one — and then it is run past a gate that can only make the verdict worse.
The 8 signals
| Signal | Role |
|---|---|
| customer_id (not PII) | signal |
| full_name (low) | signal |
| email (moderate) | signal |
| phone (moderate) | signal |
| ssn (regulated) | top trigger |
| dob (moderate) | signal |
| plan (not PII) | signal |
| signup_ip (low) | signal |
The verdict bands
One regulated column left exposed holds the whole dataset - HOLD regardless of how many columns are clean. 83% handled with an open SSN column is still a HOLD.
In the worked sample 7 of 8 columns handled, 83% of PII (weakest 0) and it still reads HOLD — Every column is handled except the SSN, which is regulated and stored unmasked - one regulated column exposed - so the dataset is HOLD even at 83% of PII handled. The one thing to fix first: ssn - mask, tokenize, or encrypt the SSN column before the dataset moves anywhere; a regulated field in the clear holds everything..
Common questions
Can a profile look clean on the PII Detection for Structured Data and still fail?
Yes. The verdict is the weakest of 8 signals, then run past a worsen-only gate — the Regulated-exposed gate — that can only make it worse. In the worked sample 7 of 8 columns handled, 83% of PII (weakest 0) and it still reads HOLD, because every column is handled except the SSN, which is regulated and stored unmasked - one regulated column exposed - so the dataset is HOLD even at 83% of PII handled.
What is a worsen-only gate?
A dispositive rule that can only lower a verdict, never raise it. One fatal flaw overrides an otherwise-clean sheet, because a single disqualifying gap shouldn't hide behind everything that passed. The tool also names the one thing to fix first — here, "ssn - mask, tokenize, or encrypt the SSN column before the dataset moves anywhere; a regulated field in the clear holds everything.".
Grades handling you describe against each class's minimum, not your regulatory obligations. Not legal advice.
Embed this diagram
Free to share and embed with attribution (CC BY 4.0) — keep the link to redhub.ai.
Interactive — renders the live diagram
<iframe src="https://redhub.ai/visuals/tool/pii-detection-structured-data.html" title="How the PII Detection for Structured Data gate works — RedHub AI" width="760" height="1650" loading="lazy" style="border:0;width:100%;max-width:760px"></iframe>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai/visuals/tool/pii-detection-structured-data">How the PII Detection for Structured Data gate works</a> — by <a href="https://redhub.ai">RedHub AI</a>, the AI that tells you when to doubt it.</p>Image + link — a static picture for any blog
<a href="https://redhub.ai/visuals/tool/pii-detection-structured-data"><img src="https://redhub.ai/visuals/tool/pii-detection-structured-data-share.png" alt="Diagram of PII Detection for Structured Data: eight columns graded, a regulated-exposed gate, and a dataset reading HOLD with an open SSN column at 83% of PII handled." width="760" loading="lazy" style="max-width:100%;height:auto;border-radius:16px"></a>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai">RedHub AI</a> — the AI that tells you when to doubt it.</p>
This is how PII Detection for Structured Data works. More diagrams in the Visual Field Guide.