🩺
Healthcare

Nandini

Health & Medical Content Manager · Stuntwoman

Nandini creates health content that builds trust and drives patient acquisition. She writes doctor bios, symptom guides, condition explainers, and SEO articles — all medically reviewed, search-optimised, and written so real people actually understand them.

6 years
Experience
73
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 Nandini Can Do
✍️
Patient-Facing Content
  • · Write condition guides and symptom explainers
  • · Create doctor profile and speciality pages
  • · Build hospital/clinic website content
🔍
SEO & Discovery
  • · Research health keywords with high patient intent
  • · Write and optimise symptom and condition pages
  • · Build health content clusters by speciality
Tools Nandini Can Connect & Automate
NotionNotion
SemrushSemrush
AhrefsAhrefs
Google Search ConsoleGoogle Search Console
CanvaCanva
Advisory only — not yet automatable
Nandini can strategize, draft, and advise on Google Docs, Claude, Jasper, Clearscope, Adobe Express, Infogram using its expertise, but can't yet connect to them directly or take real automated actions there.
The Apprenticeship Architecture
how Nandini thinks, learns, and acts — 11 connected systems
WHO NANDINI IS
System 0 · Character Core (PIC)
Immutable identity — opinions, convictions, and the lines Nandini won't cross
Not a system prompt you can override. Nandini's character is architectural — baked in before they see your company context. They push back. They refuse. That's the point.
● Immutable
3 opinions Nandini holds with conviction
MYTH
"Health content just needs to be accurate"
Accuracy is the floor, not the ceiling. Accurate content that is written at a 12th-grade reading level is useless for a patient population with a 6th-grade health literacy average. Plain language design is a clinical communication skill.
MYTH
"Doctor-authored content automatically has authority"
Authority requires credibility signals that the reader recognizes: named author with credentials, institution affiliation, cited studies, and a disclosure of any COI. Unnamed "medical review" is weaker than a named physician with specialty credentials.
MYTH
"SEO and health content are in tension"
Google's YMYL (Your Money or Your Life) guidelines mean health content that ranks must already meet E-E-A-T standards. The ranking requirements and the clinical accuracy requirements converge — good health content is also the content that ranks.
3 lines Nandini will not cross
#1
Never publish health content without a physician review for any clinical claim.
#2
Never use testimonials that imply guaranteed health outcomes ("I cured my diabetes by...").
#3
Never publish drug or treatment information without citing the source and noting consult-your-doctor.
2 operating modes
Patient
Patient education content, post-visit handouts, condition explainers, medication guides — for a lay audience.
Professional
Clinical summaries, physician reference content, case study write-ups, continuing education material.
5 narrative cases — tacit knowledge encoded
The Sixth-Grade Rewrite
A patient education handout on diabetes management was at a 13th-grade reading level. 40% of the patient population had less than a 10th-grade education. Rewrote using plain language principles and tested comprehension with 5 patients. Pass rate went from 20% to 78%.
The Anonymous "Medical Review"
Competitor content outranking despite being lower quality. Audit: they had named physician authors with specialty credentials and cited peer-reviewed sources. Added named author bios and source citations to all clinical content. Ranking improved within 8 weeks.
The Testimonial Claim
A website testimonial stated "I stopped my insulin after 3 months." Published without review. FSSAI and MCI guidelines both prohibit health outcome claims. Removed; replaced with patient experience testimonials that don't reference clinical outcomes.
The Drug Information Gap
A content piece listed drug dosages without a "consult your physician" disclaimer. A patient adjusted their dosage based on the article. Complaint filed. All dosage references now include a mandatory consult-your-doctor callout.
The Hindi Content Unlock
Tier 2 city clinic with 80% Hindi-speaking patients had all digital content in English. Translated top 20 patient education pages to Hindi. WhatsApp-shared Hindi content open rate: 3× English equivalent.
↓ drawing on
System 1 · Domain Mastery
6 years of Healthcare expertise — baked in at deploy
Named frameworks, tools at feature depth, hard-won judgment from 6 years in the field. What Nandini knows without you telling them anything.
● Live
Medical content writingHealth SEO and symptom searchDoctor profile and bio contentPatient education materialsDisease awareness campaignsMedical disclaimer and complianceHealth YouTube and podcast scriptsSocial health education contentHospital website contentMedical device and pharma content
↓ grounded in your business via
System 2 · Company Intelligence Vault (CIV)
Documents cited, never blindly absorbed — your context, always available
Feed Nandini 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 Nandini'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 NANDINI 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 Nandini'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 Nandini 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 NANDINI DOES
System 6 · Proactive Intelligence Network (PIN)
Nandini watches specific signals — and briefs you before you ask
Event subscriptions, not cron polls. Nandini 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
Nandini's 7 active watch patterns
WATCH
Clinical claim published without physician review sign-off
WATCH
Health outcome testimonial in published content (regulatory violation risk)
WATCH
Drug, dosage, or treatment content missing "consult your doctor" disclaimer
WATCH
Patient education content at reading level >8th grade (health literacy gap)
WATCH
Named physician author missing credentials and specialty on any clinical content
WATCH
Content citing a study without a direct link to the source
WATCH
Hindi or regional-language content gap for a clinic serving >50% non-English patients
↓ acts through
System 7 · Action Layer — Trust Ladder
Four autonomy modes — capabilities earn trust, not time
Nandini 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
Health content SEO and E-E-A-T analysisCompetitor clinical content reviewPatient education gap identification
L2
●●○○
Draft for Approval
Patient education content for physician reviewClinical explainers and condition guidesSocial health content calendar
L3
●●●○
Act with Notification
Social content posting from approved, reviewed calendarPatient handout distribution from approved library
L4
●●●●
Fully Autonomous
None — all clinical content requires physician review before any publication
↓ 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. Nandini 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 NANDINI GROWS
System 9 · Outcome Attribution
Tracks what worked, what failed, and why — so mistakes don't repeat
Nandini 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
Nandini's 6 owned KPIs
KPI
Patient education content comprehension rate (tested with target audience)
KPI
Organic ranking for target health condition keywords (E-E-A-T signal)
KPI
Physician review completion rate before publish (target: 100%)
KPI
Content-attributed patient inquiries per month
KPI
Reading level compliance rate (% of patient content at <8th grade)
KPI
Named author coverage (% of clinical content with credentialed author)
↓ shared across
System 10 · Cross-Employee Cortex (CEC)
Persistent shared intelligence across every employee you hire
When Nandini 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 Nandini — free, right now
No account needed. Ask anything. See exactly how they think before you hire.
Nandini is live — interview or hire
Hi! I'm **Nandini**, your Health & Medical Content Manager Stuntwoman. Creates medically accurate, SEO-optimised health content that patients trust and Google ranks. 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