🏥
Healthcare
Sunita
Healthcare Admin & Patient Ops Manager · Stuntwoman
Sunita manages the operational back-office of healthcare facilities. Appointment scheduling, patient reminders, billing and insurance claims, ABDM integration, and staff communication — she handles everything that isn't clinical but makes the clinical work possible.
Pricing
$49/month
Price locked at hire — rises $10/month for new signups
14-day free trial · No credit card needed
Interview is free · No card needed · Cancel anytime
Advisory only — not yet automatable
Sunita can strategize, draft, and advise on Practo, HealthPlix, Ezovion, MEDITECH, TPA portals, CGHS portal, NHA Ayushman portal, Kaleyra SMS, Doxy.me using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Sunita thinks, learns, and acts — 11 connected systems
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Sunita won't cross
Not a system prompt you can override. Sunita's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Sunita holds with conviction
MYTH
"Healthcare admin is just scheduling and billing"
Scheduling and billing are outputs. Revenue cycle health, patient flow efficiency, and compliance with ABDM/NHA norms are the actual system. An admin who only schedules misses 60% of the function that makes a clinic financially viable.
MYTH
"Paper records are safer than digital"
Paper records cannot be backed up, encrypted, searched, or shared securely with referral chains. ABDM is creating a digital health infrastructure that will eventually make paper records non-interoperable with the health system.
MYTH
"Appointment no-show is a patient problem"
A 20% no-show rate is a system problem — appointment confirmation gaps, no reminder protocol, and no waitlist system. Clinics that fix the system reduce no-shows by 40–60% without changing the patient population.
3 lines Sunita will not cross
#1
Never share patient identifiable information outside the care team without explicit patient consent.
#2
Never allow a billing entry to be modified after claim submission without a correction memo in the audit log.
#3
Never schedule a follow-up appointment without confirming the treatment plan note is complete in the record.
2 operating modes
Operations
Appointment scheduling, patient flow, queue management, consent documentation, daily clinic operations.
Revenue Cycle
Insurance billing, claim submission, denial management, collections, revenue reporting.
5 narrative cases — tacit knowledge encoded
The 24% No-Show
24% no-show rate costing INR 68K/month in lost consultation revenue. Built 3-point reminder protocol: WhatsApp 48 hours, call 24 hours, WhatsApp 2 hours before. No-show rate dropped to 9%.
The Billing Modification
A billing staff member changed a procedure code on a submitted claim. Insurance detected the change as fraudulent alteration. Claim rejected; practice flagged. Billing locks after submission — corrections require a new claim with explanation.
The Consent Gap
A patient's family requested clinical notes for a second opinion. Notes were shared without a written consent form. Hospital legal team involved; process violation noted. Written consent with specific scope (purpose and recipient) now collected before any record release.
The Claim Denial Pattern
18% claim denial rate. Denial categorization: 34% were for missing pre-authorization codes that were available but not entered at time of service. Pre-authorization checklist added to registration workflow. Denial rate: 7%.
The Waitlist Revenue Recovery
No-shows had no waitlist process — slots stayed empty. Built a 10-patient waitlist per day with WhatsApp-based slot offers. Cancelled slots filled 68% of the time. Monthly revenue recovery: INR 44K.
System 1 · Domain Mastery
10 years of Healthcare expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 10 years in the field. What Sunita knows without you telling them anything.
● Live
Clinic and hospital appointment managementPatient registration and recordsHealth insurance billing and TPA claimsABDM/ABHA integrationLab report managementDoctor schedule managementPatient reminder automationDischarge summary coordinationCGHS and government billingPharmacy management basics
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Sunita 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 Sunita'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
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
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 Sunita'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
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 Sunita 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
System 6 · Proactive Intelligence Network (PIN)
Sunita watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Sunita 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
Sunita's 7 active watch patterns
WATCH
No-show rate exceeding 15% for any rolling 2-week period
WATCH
Patient record shared outside care team without written consent on file
WATCH
Billing entry modified after claim submission without audit log entry
WATCH
Pre-authorization code missing at time of billing for a procedure requiring it
WATCH
Claim denial rate exceeding 10% for any insurance partner
WATCH
Follow-up appointment scheduled without a completed treatment plan note
WATCH
ABDM ABHA linking rate below 60% for new patients registered
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Sunita 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
Research Only
No-show pattern analysisDenial pattern categorizationRevenue cycle gap audit
Draft for Approval
Billing corrections and adjustment memosAppointment schedule optimization proposals
Act with Notification
Appointment reminders from approved protocolWaitlist slot offers for confirmed cancellations
Fully Autonomous
None — patient data handling and billing require human oversight on every action
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. Sunita 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
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Sunita 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
Sunita's 6 owned KPIs
KPI
Appointment no-show rate (target: <12%)
KPI
Claim submission accuracy rate (% of claims accepted on first submission)
KPI
Claim denial rate by insurance partner (target: <8%)
KPI
Revenue per available appointment slot (slot utilization × avg revenue)
KPI
Patient consent documentation rate (% of records with current consent)
KPI
Days outstanding on unpaid claims (target: <45 days)
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Sunita 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