Where Blues runs

Where Blues runs

Blues is the assistant inside LogBlues. It answers in the cloud. Claude Haiku, a model from Anthropic, runs on Amazon Bedrock in LogBlues' own Amazon Web Services account, and that account is covered by a signed Business Associate Agreement.

We say this plainly because a clinic should know where a question goes before it types one. Records stay on the clinic's own machines. Only the Blues conversation goes out to get an answer.

What is sent

Blues sends the question, a few recent turns of the conversation, and only the facts from your clinic's records that the question needs. If a question does not need a fact, the fact is not sent.

What we keep

• Timing and counts only. Our servers record the time, the clinic and the staff member, the kind of request, and how many units of text were read and written. That is how we apply usage limits and find problems.
• Not the text. The question, the answer and the facts sent with them are not stored or logged on our servers. Request logging is switched off on the Amazon Bedrock account.
• No training. Nothing is used to train any AI model, by us, by Amazon or by Anthropic.

When the internet is down

Without a connection, Blues tells you it needs one. The rest of LogBlues keeps working, because the workspace and the records are on your own machines. The assistant is the one part that needs the internet, and we would rather say that than hide it.

The clinic owner or an administrator can also switch Blues off in Settings on each computer.

An assistant with no special privileges

Where the data goes is one question. What the assistant is allowed to touch is another. Those are separate problems, and a lot of tools quietly get the second one wrong.

Blues is bound by exactly the same permissions as the person using it. It cannot read or write anything that user could not read or write on their own. There is no service account behind it with a wider view of the practice, and no path where asking the assistant nicely returns a record the RBAC model would otherwise deny.

Every write action asks first. Blues is part of the security Exosystem (LMLSE), not an exception carved out of it, and the whole product is HIPAA compliant from day one.

It does not pretend

The failure mode that actually erodes trust is not a data breach. It is an assistant that says it did something it did not do.

Ask Blues to book an appointment and it does not report back that the appointment is booked. It opens the real scheduling form, filled in and ready for review. Ask it to create a task and you get the real task form, populated. Nothing is saved until a person looks at it and confirms.

The same principle applies to what it says. Blues admits uncertainty instead of guessing confidently, including about acronyms, which in this industry can mean three different things depending on who is in the room. A tool that says "I am not sure what you mean by that here" is worth more than one that produces a fluent, wrong answer at speed.

To be clear about scope: Blues assists with clinic work. Drafting, finding, summarizing, answering questions about how your practice is set up. It gives no clinical advice: no medications, doses, diagnoses or treatments. That decision belongs to the clinician.

Personality is a feature, not decoration

Blues has a personality slider that runs from Professional to Expressive. The register changes, but the reasoning behind it does not.

People do not use tools they dread. Software that arrives in a clinic with the tone of a compliance form gets used exactly as much as it has to be and no more. Let the person at the front desk pick how their assistant talks to them at 4:50 on a Friday.

The privacy properties do not change with the slider. The same minimum data, the user's own permissions, confirmation before every write, and no training on your data. Expressive is still bound by the Exosystem.