A child sitting cross-legged

“I initially thought that you and Mom invented this diabetes to control me.”

— A founder’s son, on diagnosis day

Foxy

“You become responsible, forever, for what you have tamed.”

— Saint-Exupéry, The Little Prince

Please help us to build Foxy — an AI-powered conversational companion for kids living with chronic conditions like obesity, diabetes, and such like.

I suppose that some of you, or maybe your friends, share my pain of being a parent to a child with a clinical condition — or deal with this professionally. Our small team strongly believes in co-creation when it comes to innovative products. We invite you to join our community of like-minded people that will, through comments and suggestions, help us build an excellent product.

We need all sorts of advice, namely:

  1. How should we change the design — scene, character, voice, and so on?
  2. What would you, as caregivers, like to know about how kids with clinical conditions feel — what they think about their condition, what problems they might have with their peers, and even with parents sometimes?
  3. Any other comments and suggestions you may venture to express.

— Igor, co-founder

For potential partners and investors →
Digital therapeutic · Adherence & concordance · Children 5–12 first

Companions that hold the line for kids living with chronic conditions.

DiaHeroes is a digital therapeutic for adherence and concordance in children living with chronic disease. We start with type 1 diabetes, ages 5–12 — the hardest case, and personal to two of three founders, who are parents of kids with T1D — and we’ve built the architecture to extend to every form of diabetes, childhood obesity, asthma, celiac disease, and epilepsy. A small fox named Foxy, who has diabetes too, keeps the daily routine bearable.

See what it is → Talk to the founders →
Foxy character

A child with a chronic condition lives in a world where forgetting lunch is not a small thing. A companion that does not register the asymmetry between “forgot lunch” and “had a great lunch” is a companion that has nothing to teach.

— From the design account

DiaHeroes app showing schedule dial and Foxy character

●  Live build · iter 13

01 · The problem

Adherence is the hard part, and it’s where outcomes live or die.

Children living with chronic conditions face routines that do not negotiate. For a child with type 1 diabetes that means up to twenty events a day — meals, glucose measurements, insulin timing, exercise, sleep — all on a schedule the disease imposes and the child must keep. For a child with asthma, epilepsy, or celiac disease, the structure is different but the shape is the same.

The medical evidence is unambiguous: adherence is the dominant lever for long-term outcome, and adolescence is where it most often breaks down. The clinical literature is full of interventions that work in the clinic and fail at home.

The reason is not that children don’t care. The reason is that the routine is unfair, and existing tools either pretend it isn’t — cheerful gamification that wears off — or punish the child for slipping, producing apps the child stops opening. Neither holds.

DiaHeroes is the third option: a companion that names what is unfair, holds the line anyway, and stays warm on the bad day. Adherence — what actually got done — is the measurable surface; concordance — genuine agreement about the plan, not mere acceptance — is what makes it durable. Adherence without concordance is fragile; concordance without adherence is hollow. The product pursues both.

21%
of children and adolescents with T1D meet the glycemic targets set by the American Diabetes Association.
ADA · 2023 Standards of Care
~1M
children aged 0–14 living with type 1 diabetes worldwide. Childhood obesity (~160M), asthma (~45M), celiac disease (~12M), and epilepsy (~6M) widen the same problem.
IDF · WHO · global pediatric data
Up to 20 events
a day a child with T1D is asked to handle. The schedule is the disease — and it is the lever the companion learns to support.
DiaHeroes schedule model
02 · The framework

Three ways to live with a hard contradiction. Only one is sustainable.

Living with a chronic condition is, structurally, an exercise in holding a contradiction every day. The body wants what the condition forbids. Pediatric care recognizes three modes a child can settle into. Our companions are built around the third — and because the framework is about the structure of the contradiction, not the specifics of one disease, it travels.

a.
Denial

The kid pretends the condition isn’t there. Eats whatever, hides from consequences, skips medications. Well-documented in adolescence; precedes the worst medical outcomes. Cheerful gamification reinforces this mode.

b.
Cynical resignation

The kid acknowledges everything cynically, complies grudgingly. Develops the depression and disengagement clinicians fear. Punishing or scolding tools reinforce this mode.

c.
Tensioned dwelling

Yes, this is unfair. Yes, I have to take the medication / measure / pace myself anyway. Both true. Held without collapse. The child remains agent of their own care. This is what’s associated with strong long-term outcomes.

DiaHeroes thesis
Foxy holds the tension. He does not let the kid into denial — no pretending the routine doesn’t matter — or into cynicism — no “fine, whatever” — and he does not crush them on the bad day. The same posture works for any condition where a child must keep a routine the body resists.
03 · From T1D to a platform

Same problem shape. Different conditions.

The structural problem we solve is not specific to glucose. It’s the problem of a child living with an unfair routine that does not negotiate, where adherence is the dominant outcome lever and where existing tools fail by being either saccharine or stern.

That problem appears, with the same shape, across pediatric chronic disease. We start with type 1 diabetes because it is the hardest case — densest schedule, most unforgiving consequences — and because two of three founders live it as parents. T1D-first is evidence of capability, not the ceiling.

The architecture — the framework, the stance-space adherence metric, the anti-guilt calibration of Foxy’s state, the structured memory, the principled tone — is condition-agnostic. The product roadmap is condition expansion, not feature expansion.

Now
Type 1 diabetes (T1D), children 5–12
The flagship. Densest schedule, founder-personal. Validates the architecture under the hardest conditions.
Next
Diabetes — any form, any age
The mission covers patients of any age and any form of diabetes; the flagship architecture extends outward to adolescents and adults.
Adjacent
Childhood obesity & asthma
~160M children with obesity, 30–50% program dropout within six months; ~45M with asthma, preventer adherence ≤50%. Same shape of problem.
Further
Celiac, epilepsy & other chronic conditions
~12M children with celiac disease (teen diet lapses 40–54%); ~6M with epilepsy (~58% non-adherent in the first six months). Anywhere daily routines, motivation, and partnership determine outcomes.
04 · A day with Foxy

What the companion actually does, hour by hour.

Up to twenty events, end-of-day reflection, and a small fox whose mood tracks the day. Below is a representative T1D day — not a marketing scenario. Real schedule, real prompt structure.

07:00
Wake
App opens. Foxy greets. If yesterday’s session left a topic open, Foxy picks up the thread by name — the kid’s topic, remembered.
07:30
First measurement
Tap-to-confirm. The dial fills. Every care event resolves to a status and adherence is computed silently — the kid sees a friend’s day, not a dashboard, and is never scolded.
08:00
Breakfast
The meal triplet — measure before, eat, measure after — escorted step by step, every step deferring to the caregiver. In the gaps, Foxy talks about anything the kid wants — ships, dinosaurs, school — and actually remembers across days.
10:00 – 16:45
Snacks, lunch, school, more measurements
Schedule events surface as taps. If the kid skips, the dial registers it without drama; Foxy’s visible state dips slowly and heals fast — recovery is always quicker than the slip.
20:00
Dinner
Last meal of the schedule. Foxy notes what’s been done, what’s pending. Tone calibrated by the day’s health trajectory.
22:00
Goodnight
End-of-day message calibrated to the day: a descriptive note about how the day went, plus an emotional beat. On poor days, something like: “Rough stretch for us today. Tomorrow is a place to start.”
05 · What we built

A system, not a chatbot.

Behind the fox: a measurable adherence model, durable per-child memory, structured prompt architecture, and clinical-safety constraints. Each piece earns its place by addressing a specific failure mode that an off-the-shelf LLM would otherwise produce.

01

Adherence as a position, not a score

Every care event ends in a status, and the day reads as three percentages — engaged, went-through-the-motions, refused — the kid’s distance from each of the three modes. One physical act yields exactly one record, so the distances never lie. Tunable per condition.

02

Anti-guilt calibration

Foxy’s visible state falls slowly and recovers fast, with a hard floor: the worst Foxy ever has is “a rough stretch” — never “dying because of you.” Returning after absence meets a glad fox, not an accusing one. No numbers in the kid’s face.

03

Bounded, de-identified memory

Each visit feeds a growing, de-identified picture of the kid: interests, worries, and — beyond what adherence data can show — their attitude to the condition. The question repertoire behind it was co-designed with a professor of clinical diabetes psychology.

04

Rituals of friendship

A child who talked about ships yesterday is asked, today, whether they’d like to continue. The morning measurement is the kid’s visit with Foxy; the bedtime cycle closes the day like a conversation with a friend. Ritual is what makes the character real.

05

The hybrid firewall

Nothing the kid says to Foxy ever reaches the parent — the parent app sees categorical patterns only. In the other direction, a parent’s concern can shape Foxy’s curiosity, but it arrives rewoven into Foxy’s own voice, never attributed. Friends keep confidences; the architecture enforces it.

06

One Foxy, three apps

Three surfaces: the kid app; FoxyButton, keeping a floating Foxy present while the app sleeps; and DiaParent for the caregiver. Underneath: cooperating agents sharing one voice and one transcript — in English, Russian, and Hebrew from the start.

06 · Where we are

Working software, clinical pipeline, principled design.

13
Iterations of the dialogue subsystem shipped and tested.
Architecture stable
3
Languages supported. Persona and voice cohesive across all three.
EN · RU · HE
up to 20
Daily events tracked per child, with adherence math and engagement scoring.
Production schedule
Q3 26
Planned start of clinical evaluation in a major university hospital.
Protocol drafted
Roadmap
Now
Memory architecture closed. Continuity, anonymity, smart truncation all shipped and tested in iter-13.Working software on Android. Working MVP for parents. Web application for registration and initial survey. Pilot feasibility study commences this week.
Next month
Engagement formula calibration on real usage data. Wellbeing check-ins.Real children, real schedules.
Next quarter
Concordance. App-mediated negotiation of the regime between child, clinician, and parents — bilateral, provisional, and floored by the clinician. Easier-and-followed beats stricter-and-not-followed; Foxy is the mediator, never a party.Clinically grounded; multi-stakeholder by design.
Clinical evaluation protocol with university hospital partner. Evidence base for the framework.Drafting in progress.
Next year Q1
Parent companion app with empty-mouth mediation; iOS port; expanded language coverage; first non-T1D condition in pilot.Architecturally prepared.
07 · The intellectual foundation

The design rests on a framework, written down.

The fox is the friend who says: this is hard and unfair, AND we measure anyway, AND we get a tale after, AND tomorrow is a new day. Foxy holds the tension.

— From the DiaHeroes Bible

Most companion apps are designed by tone preference. DiaHeroes is designed from a written framework — the team’s Bible — that connects pediatric medicine, developmental psychology (Kohlberg), and a particular philosophical claim: that moral seriousness is the work of staying with a contradiction one cannot resolve.

The relationship itself is drawn from Le Petit Prince: shared experience, asymmetric agency. Foxy has diabetes too; the stance written as the seed of every prompt is “we suffer, you can save or worsen.” The clinical routine becomes the ritual of a friendship — not a chore the fox supervises.

That framework is not decoration. It generates the design choices: the stance-space adherence metric, the anti-guilt calibration of Foxy’s state, the privacy firewall, the refusal to gamify or to scold. Every parameter is defensible from the framework, and revisable if the framework changes. And because the framework is condition-agnostic, the same posture extends naturally to every form of diabetes, and to obesity, asthma, celiac disease, and epilepsy.

This matters for clinical partners, for regulators, and for parents: we can answer the question “why is the app shaped this way?” with more than “it tested well.” The shape follows from a position that has been written down and can be examined.

Request the design account →
08 · Privacy, anonymity, and AI safety

Built for kids — with the guardrails that implies.

Four questions any pediatric AI product must answer plainly: how is the child’s identity protected, what does the parent get to see, where does the clinical line sit, and how is the model kept on age-appropriate ground? Below, the position in plain language; formal policy text follows where it exists.

Anonymous by design

Registration is anonymous from the first tap. A child signs up without name, email, phone, or any other identifier. Each user is identified internally by a six-digit code and a four-digit password — that is the entire account. All data on our servers is stored against that code and nothing else.

When physiological data flows into the system — for example, glucose readings or HbA1c — it is conveyed by the patient’s clinician, within the existing clinical relationship, using only the six-digit code. We never receive the patient’s name, contact details, or any other identifier through that channel.

The one place this calculus changes is direct CGM integration. Logging into a CGM data store will, by the nature of those systems, require personally identifying credentials. When we ship that integration we will treat it as a regulated data path and comply with the applicable laws and standards explicitly — not retrofit them.

Formal policy text

Currently, user registration and use of the app are completely anonymous. Users register without providing personal information and are then identified by a 6-digit code and a 4-digit password. All user information is stored on our servers only under this number. We do not ask users to provide contact information, names, or other personal information.

As to personal information required to get access to a patient’s CGM data, the access to this data is performed by the patient’s doctor within the framework of usual clinical practice. When conveying information about physiological data (glucose levels, glycated hemoglobin and other) to the application owners, the doctor will always use only the 6-digit code of the patient without disclosing any personal data identifying the patient (names, contact information, etc.).

In the future, when integrating with CGM systems, we will require personal information to log in to the CGM data storage system. When this option is implemented, we will ensure compliance with laws and regulations taking this into account.

A firewall between kid and parent

Nothing the child says to Foxy is readable by the parent. The parent app surfaces categorical patterns and population-grounded coaching prompts — never utterances, quotations, or topics as said. Children disclose to Foxy what they would not disclose to people; that disclosure is what makes the system work, and it survives only if the confidence is kept. The firewall is disclosed to parents honestly — a surface they are told about, not something hidden from them.

In the other direction there is a soft seal: a parent’s concern may inform what Foxy gets curious about, but it reaches the child rewoven into Foxy’s own voice, never attributed. Foxy never says “your parent asked me about this.”

Clinical scope, drawn on purpose

DiaHeroes is a digital therapeutic for adherence and concordance — not medical-grade decision support, and never a substitute for clinical judgment. In the kid-facing app the line is hard: insulin is never named, asked about, quantified, or tracked by any agent; glucose values are never characterized as good or bad — the child’s own reflection is invited instead; and treatment questions get warmth plus a caregiver deferral, every time.

The clinician sets a non-negotiable floor beneath every schedule negotiation. Above the floor the child has real say; below it, the matter returns to the clinician.

AI on a short leash — and red-teamed

Letting children aged 5–12 talk to a generative model raises an obvious worry: that the conversation drifts somewhere it shouldn’t, or that a curious child finds a way to push it there. Foxy’s prompt structure encodes the audience explicitly — tone, vocabulary, and topic boundaries are calibrated to the age range and held by the system, not by goodwill.

We also know that some children are creative about jailbreaks, and we treat that as a design problem rather than a hope. Before any patient testing, a dedicated red team is tasked with attempting to subvert Foxy — trying to elicit inappropriate language or topics — and the prompt architecture is hardened in response. The findings feed back into the system before children see it.

Formal policy text

The use of artificial intelligence by children and adolescents raises concerns about the possibility of discussing inappropriate topics or using inappropriate language. With this in mind, the AI prompts are designed with a reminder that users are aged 5–12 years old and should adhere to the ethical context and content of communication within the appropriate age range.

However, there are known cases of “creative” children and teenagers learning to “hack” the AI and access inappropriate content. To prevent such cases, before testing the DiaHeroes app on a control group of patients, a team of testers was tasked with attempting to “hack” the AI dialogues and access inappropriate topics or language. The results of this test will be used to refine the prompts to prevent such situations.

Get in touch

For investors, clinical partners, and thoughtful collaborators.

If you work with pediatric chronic disease, run a clinic that wants to evaluate the system, or are looking to back work where the philosophical foundation matters as much as the product — let’s talk.

Email the founders → Download the deck ↓
09 · FoxCraft

A game by a kid with T1D, for his comrades in condition.

FoxCraft is a Minecraft-style educational adventure game created by a kid with T1D for his comrades in condition. The main character, a brave little fox, helps the inhabitants of a magical voxel world cope with diabetes. The game is designed to teach children the basics of blood glucose management in a fun and safe way.

The main mission is to travel through the voxel world of FoxCraft, find “patients” (NPCs) who have problems with their glucose levels, and help them normalize their condition with the right actions. If this is not done, the patients “die” after some time. To correct glucose levels, use candies and syringes with insulin, which the little fox collects throughout the game world.

Play FoxCraft → Back to top ↑