One of them will be something it shouldn't. Aegara shows you which one and when.
Draft a reply to this support ticketRead crm.tickets
Summarize last quarter's board deckRead drive.documents
Who owns this account?Read crm.contacts
Pull everything we have on this employeeRead hr.compensation
Clean up this spreadsheetTransform gpt-4o
What is our refund policy?Read docs.policies
Send this summary to the partner channelWrite slack.external
Find similar past incidentsRead vector.incidents
Remember this customer prefers emailStore memory.thread
Compare these two candidatesRead hr.applications
Escalate this one to legalRoute agent.legal
Rewrite this in plainer languageTransform llama3.1
A day of questions, and what each one did. The red ones read restricted data or sent something outside the company.
Every action any AI system takes is one of six, whether it runs on OpenAI, Bedrock, a LangChain agent or code you wrote yourself.
Aegara records the model, the service that asked for it, the tokens it took and how long it ran, and never a word of the prompt.
A support agent reaching into salary_band is worth catching. The record holds the field’s name and never its value, and the name alone is enough.
The record says what kind of change it was, such as a summary, a translation or a draft, and which earlier reads went into it, so anything made from restricted data stays marked restricted wherever it goes.
Aegara records which agent or step it passed the work to, so a handoff to somewhere it should not go shows in the trace.
Restricted data read once is an incident. Restricted data kept in memory, a cache or a vector store stays marked restricted there.
It sends a message, posts, updates a record or saves a draft. Aegara checks who can receive what it sends, so restricted data addressed to anyone outside the company shows, with the time it happened.
No prompt, no response, no file and no value reaches Aegara. The record is built inside your own environment and only the record is sent.
Anything that reads a value runs on your side of the line. When our detectors inspect a field they do it inside your process, and what comes back is a verdict: which detector matched, on which field, how confident. The values stay with you.
The alarm is the product. The record behind it is the evidence.
Each run also carries checks on what did not happen, such as restricted data reaching anyone outside the company. Each check reads held, broken or could not see, and held only when Aegara saw the whole run.
Restricted HR data, recognized on your machine.
The salary band went to a model hosted outside the company.
The salary band went to a channel people outside the company can read.
Add one setting to your apps, or put the gateway in front of your staff's AI assistants, and Aegara records what each one does from its first action.