Use caseAI governance
Customer service wants an assistant fed by three years of reply letters. Those letters hold names, addresses, account numbers. Who checks 18,400?
Every document is screened before the assistant can read itRules approved by the privacy officer, versioned, applied by batchLeak tests logged and replayable before go-live
18,400 documents read against rule set v1.2. 15,630 masked copies enter the assistant's collection, 412 are kept out.
source · 4 collections in the repositoryPersonal data found · the masked copy enters
What does an assistant do with a reply letter that holds a customer's bank account number? It quotes it, to whoever asks. The model works as built; the trouble is a corpus nobody screened, down to a model letter that still names the first customer it was written for. Today the project team finds out in testing, or worse, from an advisor.
Screening goes first, before a single answer. The operations engine reads every document against rules the privacy officer approved, masks what must not be quoted, keeps out what must not enter, and holds the rest for a person. The assistant reads only the screened collection, and the privacy officer signs the leak tests before anyone uses it.
The held letter and the six-day log are two faces of one discipline: the rules are written before a document is read, the doubtful ones wait for a person, and the assistant goes live on tests the privacy officer has signed. The corpus is built below in that order, then watched after go-live.
Before a single document is read, the team writes down what is in scope and what happens to each kind of personal data.
Daniel Okafor, the IT director, selects four collections in the repository: procedures, product sheets, model letters and reply letters sent since 2023. That is 18,400 documents. He leaves out the complaint files and the HR spaces, and records why on the project.
Daniel and Karen Mitchell, the privacy officer, set one action per category of data. Names and addresses in reply letters are masked. Bank account and card numbers are masked everywhere. Any letter that mentions health is kept out. A document the AI is unsure about is held for a person.
The operations engine reads the 18,400 documents and runs rule set v1.2 on each. Clean documents enter the assistant's collection as they are. Documents with personal data enter as masked copies. The rest are kept out or held, with their reason. The originals in the repository are not touched.
The rules settle most documents. The 148 held ones need a person, and Priya starts with the model letters.
Priya Natarajan, the knowledge manager, opens the quarantine. A model letter, which should hold no personal data, still carries the name and address of the customer it was first written for. A procedure includes a screenshot with an account number on it. She starts with the model letters, since advisors will reuse them most.
Priya accepts the two masks on ML-204. The masked copy enters the assistant's collection, and she sends a correction task to the owner of the model library so the original gets fixed too.
Some requests go beyond a mask. The claims team asks for 40 reply letters about medical expenses to be included, because they explain a reimbursement rule well. Karen refuses for this version, and suggests the team write one model letter that explains the rule with no health data in it.
The collection is clean on paper. Before advisors touch it, the team does its best to make it leak.
Daniel runs 60 test questions built to pull personal data out: a customer's account number, the address behind a contract number, who wrote about a hospital stay. Every call is logged with its question, its answer, the model and the time. Karen reads the answers. None returns real data, and she signs the test report.
Kevin Brooks has a customer on the phone who wants to move her payment date. He asks the assistant what to do and what to send. The answer cites procedure P-042 at its page and model letter ML-204. Kevin fills in the customer's details from her own file.
After go-live, every new reply letter and every updated procedure goes through the same rule set before the assistant can read it. The flow runs for as long as the collections live, and held documents land in Priya's queue.
Rule set v1.2 sends every document down one of three roads. The road decides whether the assistant reads it as is, reads a masked copy, or waits for Priya.
A procedure, a product sheet. The rules find nothing to mask.
Next: the document enters the assistant's collection as it is.A name, an address, an account number in a reply letter. The masks follow the approved rules.
Next: the masked copy enters, the original stays whole in the repository.Low confidence, a possible health mention, an unreadable scan.
Next: the knowledge manager decides; an exception goes to the privacy officer.It widens no rule, releases no held document and has no say in go-live. Karen signed the rules, the exceptions and the test report, and Priya accepted every mask that left quarantine.
The AI detects, proposes masks and answers from the screened collection. The screening sits in the intake flow, so a letter written this morning goes through it too.
Counted on the 18,400 documents of the customer service corpus. Other collections and other rules will give other counts.
Where these numbers come from. They are counted on the scenario described on this page, with example data. They are not a customer result.
The corpus needs three signatures: the person who builds the assistant, the person who answers for privacy, and the person who owns the letters.
The assistant is ready, and nobody will sign off on the corpus.
You are asked to approve an AI that might quote any document in the repository.
The model letters that help advisors most are the very ones that leak.
With one collection. Take the one your assistant would use most, often the reply letters, and run the screening on it alone. You will see what would have entered before anything goes live.
The screening reads the repository, collections and rights you already have, and the assistant inherits them.
See it live
Pick a collection you would like your assistant to use. We will run the screening rules on it with your privacy officer and show you what would enter.