Before you put AI on your company's documents
Could an AI assistant leak your company's information?
Your legal team has said information can't leak between departments, or be exposed by accident. These short guides explain, in plain English, how an AI assistant could do both, what to ask before you approve one, and how a well-built system prevents it.
The short answer
Can it really leak our information?
Yes, if it's built carelessly. It can put text from files a person was never allowed to open into the answers it gives them. Built properly, it follows the same access rules your files already have, and checks them before it reads anything.
The everyday picture: your office has a keycard system. Your badge opens some doors and not others, and your files work the same way. A well-built AI assistant carries each file's keycard rules with it and checks your badge before it fetches anything. A careless one is a helpful colleague holding a master key.
Where the picture stops working: an answer can blend passages from many files, so the check has to happen for every passage, not once at the door.
Engineers call these assistants RAG, short for retrieval-augmented generation: the AI looks things up in your documents ("retrieval") before it writes the answer ("generation").
Start here
The questions to settle before you approve it
Each one gets short guides: a page you can read in a few minutes, and a video you can watch in less. Each ends with the questions to put to your IT team or vendor.
Could it leak information between departments?
Or show people files they were never meant to see. How it happens, and how a well-built system prevents it.
- How the assistant knows who may see each document
- Why the check must happen before it reads anything
- Keeping departments and clients apart
5 guides ready →
What should we ask before we approve it?
Plain questions for your IT team or vendor, what good answers sound like, and how to check it works before you sign off.
2 guides ready →
Could someone trick it?
Hidden instructions inside a document, and planted files that steer its answers.
1 guide ready →
Can we prove who saw what?
Keeping a record of questions and answers, and deleting things so they're really gone.
2 guides ready →
What changes when it can take actions?
Once it can send emails or update records for someone, whose permissions does it use?
1 guide ready →
Where your data goes, whether the AI company keeps it, and which laws apply are covered by our sister site, EnterpriseLLM.ai.
Why this matters
Security is where AI projects stall
of IT and security leaders named data security and privacy their top concern about generative AI.
had delayed a rollout over data security and how information is managed. The delays were about readiness, not budget.
Source: AvePoint, The State of AI 2026, a survey of 750 IT and security leaders. The survey's sponsor sells data-security software.
Where leaks happen
From your files to an answer: where information can slip out
An assistant of this kind typically takes your documents through a few steps before it answers. Each step is a place where the keycard rules can be lost. Read them all, or walk through them one at a time.
-
Your documents
What you already have, in SharePoint, Google Drive or your document system, each with its own rules about who can open it.
Can go wrong: many files are shared more widely than anyone realizes. Nobody noticed, because nobody could find them. An assistant can find them in seconds.
Ask: have we checked who can open what, before we connect it?
-
Bring in and prepare
The assistant takes in your files and cuts them into passages it can look up.
Can go wrong: if each file's keycard rules aren't copied in with it, the assistant can't respect them later.
Ask: does it copy the access rules for every document, and how quickly does it notice when they change?
-
Build the catalogs
It builds catalogs, like the index at the back of a book, so any passage is quick to find.
Can go wrong: if every department's documents go into one catalog with no walls, one search can reach all of them.
Ask: how are departments, or clients, kept apart inside the system?
-
Find the right passages
When someone asks a question, it searches the catalogs for the passages that best match.
Can go wrong: if it finds the best matches first and checks permissions afterwards, restricted text can slip through.
Ask: does it check who is asking before it reads anything?
-
Answer, with sources
The AI writes an answer from those passages and shows where each part came from.
Can go wrong: a summary, a quote or a source link can give away what's in a file the person couldn't open. A document can also carry hidden instructions that the AI follows.
Ask: what stops an answer revealing something the person couldn't open?
-
Check and keep current
The system is checked for quality and kept up to date as documents change.
Can go wrong: without a record, nobody can say who saw what. A deleted file can live on in saved copies.
Ask: can we see who asked what, and what they were shown? When we delete something, is it gone everywhere?
-
Put it where people work
In chat, on the intranet, in email, or connected to other systems so it can act, not just answer.
Can go wrong: once it can send emails or update records, it matters whose permissions it acts with.
Ask: whose access does it use when it does something for someone?
How each step works, in plain English, is on EnterpriseLLM.ai.
Who we are
Written by people who have built one
We built Arro, a platform that answers questions from a company's own documents. Keeping each person's answers inside what they're allowed to see is part of that work, and these guides come from it.
- Plain English first. Technical terms only when you'll hear them in a meeting, and always explained.
- Every fact has a source you can check.
- We never rank or score our own products. Where we describe how we built something in Arro, it's labeled.
When you're ready
Need an AI project through security review? Talk to the people who wrote this.
Moves and Measures helps companies plan and build AI assistants on their own documents, with the access rules done properly from the start.
Email Moves and Measurescontact@movesandmeasures.com