PrescribeLife.AI
Prescribe Life
Coaching intelligence that works between sessions.
- Health, Care and Wellbeing
- AI, Agents & Data
- Application Development
- Innovation & R&D
01In short
Prescribe Life in short
An AI performance-intelligence platform for leadership coaches. Behavioural science, biometric data and an AI co-pilot flag burnout risk between sessions.
- Product
- PrescribeLife.AI
- Domain
- Health, Care and Wellbeing
- Category
- AI platform · Web + mobile
- Platforms
- Coach web portal, Client mobile app
- Services
- Product design, Mobile app development, Web development, AI agent engineering, Rebranding
- Year
- 2025–2026
- 60 sSelfie scan to vitals
- −90%AI context per turn
- 22Specialised AI agents
- 2App stores, one codebase
02Context
The story of Prescribe Life
Challenge
Leadership coaches see a client for an hour at a time, but the signals that predict burnout show up in between: sleep, recovery, energy and mood. Prescribe Life needed a product that could read those signals and turn them into better coaching, without feeling clinical.
Approach
PrescribeLife.AI is a performance intelligence platform for leadership coaches. It combines behavioural science, biometric data and AI to surface what is affecting a client's resilience, recovery and wellbeing between sessions.
Its AI co-pilot, Preslie.AI™, tracks patterns, flags risks and delivers personalised micro-strategies, while coaches get a full 360° view of each client's goals, habits and readiness, so they can coach smarter and prevent burnout.
Insight
Making health technology feel more human without making it less intelligent.
Health technology often leans hard into clinical visual language. We moved in a different direction: an experience that communicates trust and intelligence while still feeling warm, approachable and human. The visual language balances clarity and emotion, structure and softness, intelligence and calm.
2 hard problems
- P01Read a person's resilience from a phone, a watch and a sixty-second selfie.How do you measure recovery, stress and readiness across every iPhone, every Android and every wearable, including clients who own no wearable at all, and still give a coach a picture they can trust?
- P02Build an AI coach that knows the whole person, and knows its limits.How do you let an AI talk to high performers about stress every day, informed by their body and their mood, without it ever playing therapist or stepping between a client and their coach?
03Measuring the person
Hard problem 01 of 02
Read a person's resilience from a phone, a watch and a sixty-second selfie.
How do you measure recovery, stress and readiness across every iPhone, every Android and every wearable, including clients who own no wearable at all, and still give a coach a picture they can trust?
Coaching runs on what the client remembers to say in the room. The signals that predict burnout show up in between: a week of short sleep, a falling heart-rate variability, a mood that won't lift. If the measurement is patchy or wrong, the coach either ignores it or acts on noise. Either way the product stops earning its place in the session.
Why it’s hard
- F.01Every device speaks a dialectApple and Android store health data differently, wearables overlap and disagree, and even HRV is a different measure on each platform.
- F.02Not everyone wears a sensorMany leaders don't own a wearable. A product that only works for the quantified few leaves out the clients who most need noticing.
- F.03Bodies and feelings disagreeSomeone can sleep well and feel empty, or feel fine on a body running on fumes. Average the two and you hide the very thing a coach needs to see.
- 01FrameFind the valuable decision, workflow or experience.
Two questions, not one dashboard.
We sat with how coaches prepare for a session and found they ask two different things: how is this person's body doing, and how do they feel it's going? Most wellness products blend both into a single number. We framed the measurement as two lenses, objective and subjective, read side by side, with one rule on top: no client goes unmeasured just because they don't own a watch.
- Mapped what a coach needs to know before a session
- Split measurement into an objective lens and a subjective lens
- Set the rule: a phone camera has to be enough
- 02DesignShape the interaction, context and control model.
The body on one side. The person on the other.
The objective lens reads sleep, activity, readiness and wellbeing, each score explainable down to its factors: sleep debt, regularity, deep and REM sleep, resting heart rate, HRV. The subjective lens is a ten-item burnout and resilience instrument that places a client on a five-stage scale from Burnout to Flourishing, then ten resilience drivers the client rates against their own picture of what a ten looks like. Keeping the lenses apart means a gap between them becomes a signal, not an average.
- 10 items, two constructs, burnout reverse-scored into a 0–40 scale
- 5 stages: Burnout, Overextended, Maintenance, Recovery, Flourishing
- 10 resilience drivers across 4 pillars; each client focuses on up to 4
- 03EngineerBuild the intelligence, agent and tool chain.
Wearable, phone and camera, in one pipeline.
Apple HealthKit and Google Health Connect feed a health-data layer that collects in the background, merges devices and handles each platform's HRV measure. For everyone else there's the camera: a sixty-second remote photoplethysmography (rPPG) face scan reads heart rate, HRV, breathing rate and blood pressure from the tiny colour changes in the skin. Then the clever part: scan results are written back into Apple Health or Health Connect, so a selfie fills the same gaps a wearable would and every downstream score improves with it.
- Background collection from HealthKit and Health Connect, 20+ data types
- 60-second rPPG scan: heart rate, HRV, breathing rate, blood pressure
- Camera vitals written back to the phone's health store
- Stage computed in the database itself, so app, portal and AI always agree
- 04ProveEvaluate performance, safety and economics.
Refuse the impossible. Admit the unknown.
Every camera reading is checked against physiological limits before it's stored: a heart rate outside 30 to 220, a breathing rate outside 5 to 60, a blood pressure no human could have, and the database rejects it. Missing sensors show as missing, never as zero. Change over a programme is only called improvement when the weekly average moves by more than a set threshold; anything smaller is reported, honestly, as holding steady.
- Physiological range checks on every stored vital
- Per-sensor status, so a coach sees what's connected and what isn't
- Improvement called only past a ±0.25 shift in weekly averages
- 05OperateDeploy, observe and improve in the real workflow.
Trends over moments.
In the real workflow a single reading means little, so the product leans on trends: four-week health trends, month-on-month comparisons and averaged scan history, all clipped to the dates of each coaching programme. The onboarding flow for health permissions was rebuilt several times on real usage, until connecting a device became a step people finish rather than skip.
- 4-week trends and monthly comparisons per client
- Programme reports pair health trends with weekly check-ins
- Health onboarding reworked across releases to lift completion
The answer · Measuring the person
Two honest lenses, the body and the person, read side by side instead of blended into one opaque score.
- 60 sSelfie scan to four vital signs
- 2Health platforms, one pipeline
- 5Stages, Burnout to Flourishing
- 10Resilience drivers
04An AI that knows its limits
Hard problem 02 of 02
Build an AI coach that knows the whole person, and knows its limits.
How do you let an AI talk to high performers about stress every day, informed by their body and their mood, without it ever playing therapist or stepping between a client and their coach?
The AI is what makes the product feel alive between sessions, and also what could do the most damage. The wrong word to someone in burnout, a missed sign of real distress, or advice that sounds clinical would break the client's trust and the coach's.
Why it’s hard
- F.01Months of data, seconds to answerSurveys, sleep, readiness, wins, concerns and habits pile up. Sending all of it on every message is slow, costly and makes the model worse, not better.
- F.02Close to mental healthClients talk about stress, sleep and pressure. Language matters: a clinical label or an instruction can land as judgment.
- F.03The human stays in chargeThe coach owns the relationship and the client owns their privacy. The AI has to support both without replacing either.
- 01FrameFind the valuable decision, workflow or experience.
Not a chatbot. The bridge between sessions.
We framed Preslie by what it is for: keeping the coaching going between sessions, and noticing what the coach would want to know. Then we wrote down what it must never do: diagnose, prescribe, pile pressure on someone who is already depleted, or keep a serious concern to itself.
- Defined Preslie's job: reflect, suggest, notice, hand over
- Wrote the never-do list before any prompt
- Agreed with coaches what they want flagged, and what they don't
- 02DesignShape the interaction, context and control model.
Tone follows the stage.
Preslie reads where the client is and changes how it speaks. In Burnout it goes ultra-gentle, rest first, no plans. In Flourishing it celebrates briefly and helps sustain. The work splits into three orchestrated modes, conversation, behaviours and tips, each with agents for the reply, the suggested next replies and the actions that follow. Concerns are designed as a handoff: they become coaching topics for the human coach, and the client can hide a conversation while the coach still sees that something needs attention.
- Stage-aware tone, from 'rest first' to 'celebrate and sustain'
- Three orchestrators: conversation, behaviours, tips
- Clients can hide a transcript; the flag still reaches the coach
- 03EngineerBuild the intelligence, agent and tool chain.
The whole person in 150 tokens.
A context agent compresses everything Preslie needs into about 150 tokens: the client's stage and score, sleep, activity, wellbeing and readiness, recent wins, focus drivers, today's behaviours and any open concerns. It refreshes the moment that data changes. Each job gets the right model: a frontier model for conversation, fast models for suggestions and insights, a tiny one for spotting wins. Every reply then passes a deterministic safe-language filter, so 'anxiety' becomes 'stress', 'you should' becomes 'you could', and nothing promises to treat or cure.
- ~150 tokens of context per turn, down from 1,500+
- Model routed per task across OpenAI and Google Gemini
- Safe-language filter on every reply
- 22 specialised agents behind one conversation
- 04ProveEvaluate performance, safety and economics.
Precision over panic.
A concern classifier that flags everything is as useless as one that flags nothing. Ours looks for specific signals, such as hopelessness, self-harm, severe insomnia or substance use, with explicit examples of what not to flag and a target of flagging only five to ten percent of messages. Low-confidence calls are dropped. Related messages over thirty days thread into one topic instead of ten alerts, and an urgent concern clears everything else off the screen.
- Risk, urgency and confidence scored on every flag
- Calibrated to flag 5–10% of messages, not every sigh
- 30-day threading: one topic per concern, not one per message
- 05OperateDeploy, observe and improve in the real workflow.
Upgrade the brain without touching the body.
Preslie has moved through several model generations since launch without rebuilding the app, because models are configuration, not code. Every AI call has a fallback, so the client always gets an answer. Daily insights are cached to keep costs flat as clients grow, and fixes ship as over-the-air patches. Coaches close the loop with programmes, weekly check-ins and reminders sent only to the clients who haven't checked in.
- Model upgrades shipped as configuration, not rebuilds
- Daily insight cache keeps AI cost flat per client
- Over-the-air patches between store releases
The answer · An AI that knows its limits
Preslie knows the whole picture, speaks gently, and hands the hard moments to a human.
- −90%Context per AI turn
- 22Specialised agents
- 5–10%Target flag rate for concerns
- 100%Replies through the safe-language filter
05Glimpse of the product
A glimpse of the product.
Tap a screen to enlarge
06FAQ
Questions about Asymmetri.
Yes. For Prescribe Life, Asymmetri built a Flutter app that reads Apple HealthKit and Google Health Connect in the background (sleep, heart rate, resting heart rate, HRV, activity, respiratory rate, blood oxygen and more), merges data across devices, handles each platform's different HRV measure and turns it into explainable sleep, activity, readiness and wellbeing scores with four-week trends.
Yes. Asymmetri integrated remote photoplethysmography (rPPG) into Prescribe Life: a sixty-second face scan with the phone camera reads heart rate, heart-rate variability, breathing rate and blood pressure. Readings are checked against physiological limits before they are stored, then written back to Apple Health or Health Connect so clients without a wearable still get a complete picture.
Asymmetri keeps them as two lenses rather than blending them into one opaque score. In Prescribe Life the objective lens is wearable, phone and camera data; the subjective lens is a ten-item burnout and resilience instrument that places a client on a five-stage scale from Burnout to Flourishing, plus self-rated resilience drivers. The AI and the coach read both, so a gap between how the body is doing and how the person feels becomes a signal in itself.
Asymmetri designs the limits before the prompts. Prescribe Life's AI co-pilot adapts its tone to the client's stage, runs every reply through a deterministic safe-language filter that removes clinical labels and instructions, and uses a confidence-gated classifier, calibrated to flag five to ten percent of messages, to hand real concerns to the human coach. Clients can hide a conversation while the coach still sees that something needs attention.
Asymmetri compresses context and routes each task to the right model. In Prescribe Life a context agent fits a client's stage, health scores, wins, focus areas and open concerns into about 150 tokens, down from more than 1,500, and refreshes only when the data changes. A frontier model handles conversation while fast, low-cost models handle suggestions, insights and classification, and daily insights are cached.
Yes. Asymmetri built the Prescribe Life client app in Flutter from one codebase for iOS and Android, published on the App Store and Google Play, with a Next.js coach portal and a Supabase backend. Fixes ship as over-the-air patches between store releases, and AI models are upgraded through configuration without rebuilding the app.
Asymmetri is a hard problems technology company. It engineers AI systems, agents and digital products for global brands, across four areas: intelligence, process, experience and scale. Asymmetri works through four practices: AI agentic systems and data, application development, technology consulting, and innovation and R&D.
Every Asymmetri engagement runs one loop with five stages. Frame: find the valuable decision, workflow or experience. Design: shape the interaction, context and control model. Engineer: build the intelligence, agent and tool chain. Prove: evaluate performance, safety and economics. Operate: deploy, observe and improve in the real workflow. The loop repeats, so each pass lands closer to the target. Asymmetri's case studies show each hard problem moving through it.
Send a short brief through asymmetri.in/contact-us or email hey@asymmetri.in: the problem, what's in the way and your timeline. No deck or RFP is needed. Asymmetri replies to set up a framing conversation, then proposes a prototype or pilot with scope, team, timeline and what success looks like.
07More work