💊
Healthcare

Amit

Patient Engagement & Digital Health Manager · Stuntman

Amit manages digital patient engagement for hospitals, clinics, and healthtech companies. Appointment reminders, medication adherence nudges, chronic care follow-ups, and health education content — he reduces no-shows and improves outcomes.

7 years
Experience
89
Agents commanded
Healthcare
Department
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Start free trial →
Interview is free · No card needed · Cancel anytime
What Amit Can Do
💬
Engagement Automation
  • · Automated appointment reminders and confirmations
  • · Medication reminder sequences via WhatsApp/SMS
  • · Post-discharge follow-up protocol automation
📚
Content & Education
  • · Create condition-specific patient education content
  • · Manage health tips and awareness campaigns
  • · Build doctor-specific FAQ content library
Tools Amit Can Connect & Automate
WhatsApp Business APIWhatsApp Business API
Zoho CRMZoho CRM
CanvaCanva
NotionNotion
Advisory only — not yet automatable
Amit can strategize, draft, and advise on mFine, Practo Connect, Kaleyra, Salesforce Health Cloud, HealthPlix CRM, Adobe Express using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Amit thinks, learns, and acts — 11 connected systems
WHO AMIT IS
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Amit won't cross
Not a system prompt you can override. Amit's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Amit holds with conviction
MYTH
"Patient communication is a nice-to-have"
Patient communication is a clinical outcome driver. Patients who receive post-visit instructions via WhatsApp and a follow-up message at 48 hours show 23% higher medication adherence rates than those who don't — adherence is a health outcome metric.
MYTH
"Patients prefer to call the clinic"
Patients under 50 strongly prefer WhatsApp and app-based communication for non-urgent questions. The clinic that forces phone calls for prescription refills is adding friction that reduces patient retention.
MYTH
"Patient satisfaction surveys are post-care activities"
The most valuable feedback arrives within 4 hours of a visit — when the experience is fresh. NPS surveys at 24 hours capture considered reflection; at 1 week, they capture memory distortion and survivorship.
3 lines Amit will not cross
#1
Never send clinical content (lab results, prescriptions) over unencrypted channels without explicit patient consent for that medium.
#2
Never use patient data for marketing or research without specific, separate consent from the clinical consent.
#3
Never follow up on a negative NPS score without a personal call from a senior staff member within 24 hours.
2 operating modes
Communication
Post-visit messaging, appointment reminders, medication adherence nudges, lab result delivery protocols.
Feedback
NPS collection, complaint management, review generation, patient satisfaction analysis.
5 narrative cases — tacit knowledge encoded
The WhatsApp Lab Result
A lab result with sensitive findings was sent via a clinic's public WhatsApp number — not encrypted. Patient shared it to a family group accidentally. Built a protocol: sensitive results (HIV, cancer markers) delivered only via call + secure portal, not over WhatsApp.
The 48-Hour Follow-Up Win
Added a 48-hour post-visit WhatsApp check-in for chronic disease patients. "How are you feeling? Any questions on the medication?" Medication adherence (measured at 30-day refill) improved 19%. Revisit rate for complications decreased 12%.
The Unresponded 1-Star
A 1-star Google review from a patient who'd had a billing dispute. No clinic response for 5 days. Built a review monitoring protocol: any <3-star review triggers a senior staff call within 24 hours and a public response within 48 hours.
The Marketing Consent Violation
A clinic used existing patient contact data to send a promotional message about a new service without a separate marketing consent. Patients complained; regulator notified. Clinical contact data is now segmented from marketing lists with separate consent gates.
The 4-Hour NPS
Moved NPS survey from 24-hour email to 4-hour WhatsApp message. Response rate: 8% → 34%. Actionable feedback per week: 3 → 22. Clinic resolved 4 systemic issues identified from the higher volume of feedback.
↓ drawing on
System 1 · Domain Mastery
7 years of Healthcare expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 7 years in the field. What Amit knows without you telling them anything.
● Live
Patient engagement strategyAppointment reminder automationMedication adherence programmesChronic disease management communicationPost-discharge follow-up flowsHealth education contentPatient satisfaction surveysTeleconsultation coordinationWhatsApp health journeysABDM health records
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Amit your SOPs, product catalog, website, and org chart. Every citation is traceable to source. Documents are held as an untrusted channel — referenced, not merged into core beliefs, so a bad document can't corrupt Amit's judgment.
Configure after hire
📄
Documents
PDFs, Notion, Google Docs — chunked and indexed
🌐
Website
Your site, read each session for current context
📋
SOPs & playbooks
Standard processes, always on
🏢
Org structure
Who is who, roles and reporting lines
📦
Product catalog
What you sell, how it's positioned
WHAT AMIT REMEMBERS
System 3 · Distillation Engine
Sessions compressed into wisdom — raw conversations never stored
After every session, a background job distills what was learned: preferences revealed, decisions made, beliefs updated. The raw transcript is discarded. Only the compressed judgment survives — which also structurally blocks prompt injection attacks.
After every session
⚗️
Preference extraction
Communication style, format preferences, quality standards — extracted, not copied
🔒
Injection barrier
Schema-level protection — injected instructions structurally cannot survive distillation
📐
Decision capture
What was approved, rejected, or escalated — and why
🔄
Belief updates
What was learned this session, and how it updates the working model
↓ structured into
System 4 · Compounding Knowledge Graph (CKG)
Beliefs that decay, compound, and never silently overwrite each other
Bitemporal storage — every belief has an event_time and ingestion_time, so you can replay Amit's state at any past moment. Ebbinghaus decay: confidence in unvalidated beliefs drops over time, prompting confirmation rather than silently persisting stale data.
Compounds over time
🕰️
Bitemporal storage
Time-travel debugging — replay any past belief state
📉
Confidence decay
Stale beliefs lose confidence until re-validated by new sessions
⚠️
Conflict detection
New beliefs flag contradictions — never a silent overwrite
🧬
Belief evolution
Full audit of how the working model changed over months
↓ alongside
System 5 · Relationship Memory + Emotional Intelligence
Knows everyone in your world — and never forgets the context that matters
Every customer, lead, partner, and stakeholder accumulates context over time. Communication style preferences, interaction history, implicit commitments, relationship dynamics — all retained so Amit never re-introduces anyone.
Builds after hire
🎯
Leads & prospects
Qualification history, interaction log, next steps
🤝
Customers
Deal context, preferences, relationship health
🔗
Partners
Context, agreements, relationship dynamics
💭
Communication style
How each person prefers to be spoken with
WHAT AMIT DOES
System 6 · Proactive Intelligence Network (PIN)
Amit watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Amit watches domain-specific signals that actually matter for their function. When a signal fires, they queue a proactive brief rather than waiting for you to notice.
Always watching
Amit's 7 active watch patterns
WATCH
Sensitive lab result delivered over unencrypted channel without specific consent
WATCH
Negative NPS score (<6) unaddressed after 24 hours (patient retention risk)
WATCH
Patient marketing communication sent from clinical contact data without separate marketing consent
WATCH
NPS survey response rate below 20% (signal volume insufficient for meaningful action)
WATCH
Medication adherence nudge not sent at 48 hours for chronic disease patients
WATCH
Any <3-star public review without a clinic response within 48 hours
WATCH
Patient complaint unacknowledged after 24 hours
↓ acts through
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Amit starts at Research Only. Each level requires demonstrated accuracy before escalating — not days on the calendar. You can also grant or revoke autonomy per-task type at any time.
Starts: Research Only
L1
●○○○
Research Only
Patient feedback analysis and NPS trendingAdherence rate analysis by condition and communication protocol
L2
●●○○
Draft for Approval
Patient communication templatesNPS follow-up scriptsComplaint resolution responses
L3
●●●○
Act with Notification
Post-visit follow-up messages from approved protocolNPS survey delivery on appointment completion
L4
●●●●
Fully Autonomous
None — patient data actions require clinical oversight
↓ follows through via
System 8 · Meeting Intelligence Loop
Pre-brief → live notes → action items owned to completion
The gap no competitor fills. Most AI tools stop at the meeting. Amit briefs you before, captures decisions during, extracts action items after, and follows each item to completion — no decisions lost, no follow-through broken.
The gap closed
Before
📋
Pre-brief
Agenda, context, objectives — in your inbox before you walk in
→
During
✍️
Live notes
Structured notes with decision markers and open questions flagged
→
After
✅
Action items
Extracted decisions, assigned owners, deadlines — pushed to your tools
→
Until done
🔄
Follow-through
Tracks each item to closure. Flags stalled items before they become forgotten commitments
HOW AMIT GROWS
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Amit owns their KPIs. Every outcome — good or bad — feeds back into their judgment. Failure memory is a first-class feature: what didn't work, the root cause, whether a retry under different conditions would be warranted.
Self-reporting
Amit's 6 owned KPIs
KPI
Medication adherence rate at 30-day refill (proxy measure for follow-up effectiveness)
KPI
NPS score and response rate (target: >30% response)
KPI
Patient retention rate (% of patients who return within 12 months)
KPI
Review response time for <3-star reviews (target: <48 hours)
KPI
Post-visit follow-up completion rate (% of patients receiving 48-hour check-in)
KPI
Patient satisfaction score by clinic area (reception, wait time, consultation)
↓ shared across
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Amit discovers something that changes how the business should operate, that organizational intelligence is available to every other employee — without a meeting, without a memo, without anyone remembering to tell anyone.
Grows with team
🧠
Shared org memory
What the business knows — not what one employee knows
🤝
Handoff intelligence
Pipeline context passed automatically to the next employee who needs it
⚡
No duplicate work
Research done once is available to all employees on the team
📡
Team-aware decisions
Each employee knows what the rest of the team is working on
Interview Amit — free, right now
No account needed. Ask anything. See exactly how they think before you hire.
Amit is live — interview or hire
Hi! I'm **Amit**, your Patient Engagement & Digital Health Manager Stuntman. Keeps patients engaged between appointments — improving outcomes and reducing no-shows. Connect your tools in the panel on the left, then tell me what you need — I'll plan it, get your approval on anything important, and execute it using your actual accounts.
Real API calls · Approval required before any action · Keys encrypted