Method
How the Profile is built.
What the picture contains
A lot happens between visits that is hard to remember.
An antidepressant decision is usually made from little data: what the patient remembers at intake and what they report next visit (which might take months).
What helps is a fuller record of what happened between visits.
Illustrative
Two accounts, both from memory
The Orchard Profile
Spoken answers, transcribed and organized by AI software
The prompts are designed, and you answer them out loud.
The app asks a small set of designed prompts each evening, and the person answers out loud. The prompts are not therapy. They don’t treat, advise or intervene. They exist so someone can describe their experience in their own language, in the moment rather than in recollection.
The sequence is designed so that a week of short answers surfaces the breadth of a person’s health, rather than circling the complaint they led with.
Over 80 domains, each drawn from the literature.
80+
3–7
Every batch of answers is read against a set of over eighty health domains drawn from the depression literature. The same frame is used every time, whatever the person chose to talk about that evening.
In addition, the Profile picks out a few personal themes that come up most in what this person says, in their own words rather than in scale language. Two people being treated for depression rarely talk about the same things.
Each theme shows how it has changed from batch to batch, anchored to something the person actually said.
That organizing is done by AI software from outside providers, following methods our clinicians wrote. AI can make mistakes, so check anything important with your prescriber.
The Profile shows what you haven’t talked about yet.
We analyze the full set of domains every time. That means the Profile shows what came up and what did not, and both appear in the app.
surfaced in the first two weeks
The remaining forty are printed as not yet talked about.
One demonstration case, not a typical figure
A report that shows only what it found invites the reader to treat silence as absence, which is one of the ordinary ways a symptom gets missed. Marking the unexplored ground points the next conversation at the faint parts of the picture.
Movement, and what moved alongside it.
Because you answer continuously, each theme carries a line rather than a point. The Profile shows how what you’ve reported about each symptom has changed week to week, and places medication changes and life events on the same timeline, so a shift can be read against whatever preceded it.
From a demonstration Profile
The Profile makes no causal claim about those associations. It sets them side by side, in order, and leaves the interpretation to you and your clinician.
What published research says about your medications.
The Profile gives information about your medications: what they’re generally studied for, which of the symptoms you track fall outside that, and questions you may want to ask your prescriber. Talk to your prescriber before changing any medication.
Every one of those statements carries a citation, and every citation is visible in the report. A prescriber can read the source rather than take the sentence on trust.
Click a citation to read its source
Sertraline is well studied for depression overall. Published research has not established an effect on early-morning waking, which you have described.
Sleep problems and tiredness are among the symptoms most often left behind in people who otherwise respond to an SSRI.
In published research, a dose increase can briefly bring on jitteriness or anxiety. Worry has come up often in your first two weeks of check-ins, which may be worth raising as a question with your prescriber.
The Profile does not select a medication, rank options, or predict how someone will respond to a drug. It assembles what the literature already says about this symptom picture and this regimen.
Auditability
Assembled in parts, so it can be checked in parts.
The report is assembled in discrete sections rather than written as one continuous narrative. Some are structured records, some are analysis, and the pharmacological section is entirely cited. Each part can be judged on its own terms, so a reader who disagrees with one is under no obligation to discard the rest.
01
Every analysis must carry its evidence before a report will assemble.
02
"Recommendation" language is blocked before a report is released.
What the Profile is not.
It is not a diagnosis
The Orchard Profile does not diagnose, detect or screen for any condition. It records what you’ve said, in your own words.
It does not choose the medication
The Profile does not select, rank, or predict a medication for anyone. It maps how symptoms present and cites what the literature says; the prescriber decides. That is the design, not a limitation of the current version.
It is not a treatment
Orchard does not claim to make anyone better. It is a record you can share with your prescriber.
It is not a substitute for care
Orchard is an information and tracking tool. It is not a substitute for care from a clinician. AI software helps create your Profile and can make mistakes, so check anything important with your prescriber, and talk to your prescriber before changing any medication.
It is not for an emergency
The Profile builds over weeks by design. If you are in crisis, call or text 988 in the US.
See the method in the app.
30 days free at launch, then monthly. Answer a few prompts and watch your Profile come together.