This is not an AI report writer. It is the reasoning layer under the whole evaluation.

Every patient, every stage, at a glance - from referral through testing to signed report.

This one shipped earlier in the year and it is the reason we are confident about the rest. It was the first time we treated the assessment as a system rather than a series of documents. Everything above is what that made possible.

Before: the caseload lived across a spreadsheet, a calendar and your memory.

Upload a report you have already written and the system extracts your phrasing, your structure, your recommendation style and how you introduce a measure - and that overrides every default.

Underneath it sit the settings a practice needs: how generated text refers to a child client, an adult client, a family or a professional; whether results are organized by domain or by measure; length, technical level, emphasis and the AI disclosure. Set once for the clinic, overridable on any single report.

Delivery carries the same identity. A designed cover with your logo and palette, or the dense traditional layout your referral sources expect, with your credentials and signature applied only after you approve.

Before: the report sounded like the tool that wrote it, and looked like everyone else’s.

Every uploaded protocol and score report is checked on arrival: patient name match, session date clarity, document source, scores present - with a confidence score attached. If a handwritten 3 could be an 8, it flags it rather than guessing.

What comes out is structured and editable: facts with the informant and confidence on each, score tables, observations. AI-derived insights are separated from raw extraction and proposed rather than assumed - you accept the ones you find clinically sound and anything you skip is discarded.

Nothing is available to the report until you approve the document.

Before: extracted data went straight into the draft, and you found the errors later, in the finished report.

Ask the case a question in plain language and get an answer drawn from that patient's own data. Why this diagnosis held. What contradicts it. How this presentation differs from a similar one you saw last month. Where a score sits against the rest of the profile.

Then ask for the change - and the report revises in place, in your voice, with the sourcing intact.

Or start from where most clinicians start.

• Defensibility check
• Peer review this draft
• Second opinion on the diagnosis
• Signals in the noise

Before: you scrolled between documents to reconstruct your own reasoning, then retyped the paragraph.

Across every measure in the case, the system surfaces cross-instrument formulations - the constellation rather than the individual scores. Anxiety-driven perfectionism presenting as a compensatory strategy. An executive functioning profile that explains an achievement gap the achievement testing alone would not account for.

Each one is presented with its central, supporting and diverging evidence, cited. You choose what carries into the report and what does not.

This is what a block editor cannot do. Assembling paragraphs is a formatting problem. Seeing a pattern across nine instruments is a reasoning problem.

Before: the constellation was there in the data. Whether you found it depended on having time for a third read.

Every diagnosis the system surfaces is tested against that patient's own dataset and presented three ways: what supports it, what converges on it from another direction, and what diverges from it.

Differential diagnosis has always required weighing the evidence that argues against you. This is the first system that puts that evidence in front of you by default rather than leaving you to remember to look for it.

Every bullet is cited to its source. You decide what carries into the report.

Before: the disconfirming evidence was in the data. Whether it reached the report depended on how tired you were.

Every generated statement carries its source on the sentence: which measure, which uploaded document, which session note, which behavioral observation you recorded at the time.

Not in a support ticket. Not on request. On the sentence, while you are reading it.

Before: you took the sentence on trust, or you went and checked it yourself.

An evaluation does not end at the report. There is the school report, the summary for the referring physician, the letter to the therapist, the plain-language guide the family actually reads.

Fourteen built-in formats are filtered by who is going to read them. Or describe the document you need in plain language and the system rewrites it into a structured brief for you to approve before it generates - each result in its own editor, each exportable.

Before: four more documents, written from scratch, in the evenings.