P4· Pharmacy and health sciences
Hospital Operations & Health Analytics
You learn to turn hospital data into dashboards a medical superintendent trusts, and to use AI on clinical paperwork while measuring exactly how often it gets things wrong.
- Who it is for
- MHA, MPH, nursing and allied health students who want to run, measure and improve how a hospital works, not just work inside it. You should have finished the common AI core. This course adds to, and never replaces, the clinical postings and training your programme requires.
- AI core
- 9 units · 20 h
- This course
- 6 modules · 12 lessons · 3.8 h
- Live projects
- 2, on Professional and Career
- Hospital Operations Executive
- Health Data Analyst
- Clinical Documentation Specialist
The skills these roles ask for. Preparation, not a promise of a job.
- Claude, ChatGPT or Gemini (free tier)Free tier
- Google SheetsFree tier
- Looker Studio (browser)Free tier
- Power BI Desktop (Windows only)Free tier
- Saarthi sandbox: synthetic hospital datasetSaarthi sandbox
- Ambient AI scribes (concepts only)Saarthi sandbox
- ABDM and ABHA (concepts only, no live integration)Saarthi sandbox
You never pay for a tool subscription. “Verified” means we checked the free access on the vendor’s own site this month. Tool names describe what you learn; no vendor endorses Launchpad.
What you will learn, in order.
Lesson films are narrated with an AI voice, over visuals made with AI tools and checked by our team. Saarthi, the coach, is an AI. Mentors and reviewers are people.
Part 1 · The AI core, shared by every stream
00Set up your coach1 hLearn how the core works, write the learning-context document that tells every AI tool who you are, and set Saarthi up as a coach that makes you think instead of thinking for you.1 h
- How this core works6 min
- Write your learning-context document8 min
- Seven roles for AI, and study modes7 min
01How LLMs work and fail2.5 hBuild a working mental model of a large language model: tokens, prediction, context windows and memory. Then learn its predictable failures (hallucination, sycophancy, stale knowledge, bad arithmetic) and reproduce them yourself.2.5 h
- Tokens and next-word prediction7 min
- Context windows and memory7 min
- Hallucination, sycophancy and other failures8 min
- Lab: one prompt, three models, five failures8 min
02Description and context engineering3.5 hWrite briefs that get the right output the first time: role, task, context, examples and format. Then make them reusable with Claude and ChatGPT Projects, Gemini Gems, custom GPTs and NotebookLM, and learn to work with PDFs, spreadsheets and images.3.5 h
- The brief: role, task, context, format8 min
- Examples and output formats7 min
- Projects in Claude and ChatGPT8 min
- Gems, custom GPTs and NotebookLM8 min
- Working with files: PDFs, spreadsheets, images8 min
03Verify everything2.5 hCheck AI output the way fact-checkers do: lateral reading, tracing citations and numbers to the original, using deep-research modes without trusting them blindly, and testing a prompt properly with a 10-case golden set.2.5 h
- Lateral reading7 min
- Checking citations and numbers8 min
- Deep-research modes: use and limits7 min
- Your first eval: a 10-case golden set8 min
04Connectors and MCP2 hConnect AI to the places your work lives (Drive, Gmail, Sheets, business data) without writing code. Learn what an MCP server is, why a reviewed directory differs from unreviewed community servers, how to grant the least access that works, and how to keep browser extensions on a short leash.2 h
- What connectors and MCP are8 min
- Trust, least privilege and the reviewed directory8 min
- Browser extensions and AI browsers7 min
- Lab: ask the seller-data MCP server, check every answer8 min
05Agents and automations3.5 hHand multi-step work to AI safely. Tell an agent from an automation, decide what to delegate, use browser and coding agents with care, and build an n8n workflow that uses AI with a human-approval step before anything leaves the system.3.5 h
- Agents vs automations: what to delegate8 min
- Browser agents, safely7 min
- Automation basics with n8n and Zapier8 min
- Lab: build an automation with a human-approval step8 min
- Failure modes and your failure-mode note7 min
06AI for learning and careers1.5 hUse AI to learn faster without outsourcing the learning, write applications that still sound like you, and practise interviews out loud with Saarthi.1.5 h
- Learning with AI, not instead of learning7 min
- Applications in your own voice7 min
- Mock interview with Saarthi8 min
07Diligence: law, ethics, integrity2.5 hThe rules that apply when you use AI in India: the DPDP Act 2023 and its 2025 Rules, academic integrity and disclosure, copyright (including where Indian law is still unsettled), and bias. You finish by writing your own AI-use policy.2.5 h
- DPDP Act 2023: personal data and AI8 min
- Academic integrity and disclosure7 min
- Copyright and AI in India8 min
- Bias and fairness7 min
- Write your personal AI-use policy7 min
08Core capstone1 hPut all four Ds together on one anonymised marketplace settlement file: ask good questions, automate one step, verify every number against Saarthi's P&L engine, and defend your work live in five minutes.1 h
- The capstone brief6 min
- Lab: ask, automate, verify8 min
- Prepare your 5-minute defence7 min
Part 2 · Hospital Operations & Health Analytics
01The numbers a hospital runs on2 lessonsBed occupancy, length of stay, turnover, OPD waits, discharge turnaround and OT use: what each one means, how to calculate it, and how to check an AI's arithmetic.2 lessons
- Eight hospital KPIs and their formulas14 min
- Calculate KPIs by hand, then check the AI's maths22 min
02Clean data and dashboards with AI help2 lessonsHospital exports are messy. Use AI to find and fix problems faster, then build a dashboard whose every number you can defend.2 lessons
- Messy hospital data and how AI helps clean it13 min
- Build an OPD and bed dashboard25 min
03Patient flow, queues and forecasting2 lessonsWhy queues form, where the bottleneck is, and how to make a simple, honest forecast of tomorrow's OPD load.2 lessons
- Why queues form: bottlenecks and Little's law13 min
- Forecast tomorrow's OPD by day of week22 min
04Clinical documentation and AI scribes2 lessonsWhat ambient scribes and drafting tools do, how they fail, and why a clinician signs off every clinical document.2 lessons
- What ambient scribes do and how they fail14 min
- Draft a discharge summary from synthetic notes25 min
05Measuring AI error rates2 lessonsGold sets, an error taxonomy, severity grades and sampling: how to turn 'the AI seems fine' into a number a quality committee can act on.2 lessons
- Gold sets, error taxonomy and severity14 min
- Run an error audit on ten AI drafts25 min
06Digital health in India and patient-data protection2 lessonsABDM and ABHA concepts, the DPDP Act and Rules, and the daily habits that keep patient data safe while you use AI.2 lessons
- ABDM, ABHA and DPDP: the rules of the road14 min
- De-identify a dataset and write a data-handling SOP24 min
Two briefs. Real-shaped work.
- Project 1
OPD wait-time and bed-occupancy dashboard
A 300-bed multispecialty hospital's medical superintendent wants one page she can open every morning: how long OPD patients waited yesterday, where they waited, and how full each ward is. Build it from the synthetic hospital dataset. Clean the data with written rules, define every metric, hand-check every number on a sample, and present it in a five-minute walkthrough with three recommendations she could act on this month.
You hand in
- A data-cleaning log: every issue found, how many rows it touched, and the rule applied
- A metric dictionary with formulas for median OPD wait, door-to-doctor time, BOR, ALOS and bed turnover
- A live Looker Studio link or Power BI file with one summary page and one drill-down page
- A check table comparing dashboard values with hand calculations for at least two departments and three days
- A five-minute recorded walkthrough and a one-page note with three recommendations, each tied to a number on the dashboard
- Your AI log: prompts used, what the AI got wrong, and how you caught it
Data: Saarthi sandbox synthetic hospital dataset, version-frozen for the cohort: 90 days of OPD registrations with timestamps by stage, daily ward census, admissions and discharges for a fictional 300-bed hospital. No real patient data.. Reviewed by Saarthi against a published rubric, signed off by a mentor.
- Project 2
Discharge-summary drafting with nurse review and a measured error rate
A hospital's nursing director is considering AI-drafted discharge summaries and wants evidence, not a demo. Using synthetic inpatient case files, design a drafting workflow, generate drafts for 20 cases, have them reviewed against gold summaries using a written error taxonomy, and report the error rate with its denominator, the severe errors, and the review steps that caught them. You do not judge clinical content yourself: a nurse reviewer (supplied by Saarthi for the cohort) grades clinical accuracy, and you run the process and the measurement.
You hand in
- The drafting prompt and the workflow diagram, showing where the nurse and clinician review and sign off
- Twenty AI drafts with source-traced annotations
- An error log using the taxonomy (omission, fabrication, wrong value, laterality, medication, follow-up) with severity grades
- Headline results: errors per 100 checked facts, share of drafts with a high-severity error, and grader agreement on a double-graded subset
- A two-page report for the nursing director: findings, limits of the test, and conditions under which a pilot could be considered
- A one-page data-handling note explaining how the workflow would protect patient data under the DPDP Act
Data: Saarthi sandbox synthetic inpatient case files (admission notes, progress notes, medication charts) with gold-standard discharge summaries confirmed by a nurse reviewer before each cohort. Fictional patients only.. Reviewed by Saarthi against a published rubric, signed off by a mentor.
In voice mock interviews and client calls, Saarthi plays: Dr. Shalini Rao (fictional), Medical Superintendent of a 300-bed multispecialty hospital in Mangaluru. She has run wards for twenty years, reads every dashboard on her phone between rounds, and has been burned by consultants whose numbers fell apart under one question. She asks how a metric is defined, which rows were dropped and why, what the AI got wrong, and who signs off clinical documents. She is warm but impatient with jargon, and she rewards candidates who say 'I don't know yet, here is how I would find out'.
On plans that include mock interviews. You get written feedback after every call.
Pick a plan for Hospital Operations & Health Analytics.
One payment. The access deadline for each plan is shown before you pay.
Foundation
01Learn the AI your field now runs on.
₹2,999
One payment. GST included.
- Access for 120 days (about 4 months) from the day you pay
- No 1:1 mentor sessions
- The common AI core and your domain course
- Saarthi, your AI coach, any hour
- Hands-on labs on free tools
- Verifiable certificate
Professional
02Prove it on real work.
₹7,999
One payment. GST included.
- Access for 180 days (about 6 months) from the day you pay
- One 1:1 session with a mentor
- Everything in Foundation
- Two live projects, reviewed by Saarthi and a mentor
- Public portfolio page of verified work
- Voice mock interviews
- One 1:1 coaching session
Career
03Work alongside our team.
₹14,999
One payment. GST included.
- Access for 240 days (about 8 months) from the day you pay
- Four 1:1 sessions with a mentor
- One 1:1 call with an industry expert
- Everything in Professional
- Four-week supervised practicum with the Saarthi team
- Four 1:1 coaching sessions with your mentor
- An exclusive 1:1 call with an industry expert in your field
- CV and LinkedIn review
- Priority mentor replies
Your access period starts the day you pay and is shown before you pay. One exam pause per enrolment, for up to 15 days. When access ends the course locks, and your portfolio page and certificate stay live. Full refund within 7 days, pro-rata after that, and an automatic refund for any practicum, 1:1 mentor or expert session we do not deliver. Refund policy