Dr. Shinde's Medical AI Innovation Hub

Empowering Medical Education through ethically-built, classroom-tested AI tools—from MBBS exam mastery to faculty productivity.

Showing 2 of 2 Tools

Biochemistry Faculty Assistant

Faculty Development

Faculty Development

Your daily co-pilot for drafting lecture notes, case vignettes, and faculty communications in your authentic teaching voice.

Context & Instructions : Use this as your "production hub" — a single place where you can create all your teaching content.
What can you ask it to do?
Draft full lectures on complex Biochemistry topics like enzyme kinetics, metabolic syndrome, amino acid metabolism, or the TCA cycle. Each lecture comes with slide-by-slide speaker notes (minimum 150 words per slide), viva questions, and common student mistakes to watch for.
Create exam questions in any format — MCQs with trap analysis (explaining why each wrong option is wrong), Short Answer Questions (SAQ), Long Answer Questions (LAQ) with marks distribution, Reasoning Questions, and Clinical Scenario Questions.
Generate clinical case vignettes set in Indian hospital contexts and aligned with NMC-CBME competencies — ready to use in Case-Based Learning (CBL) sessions with a facilitator guide included.
Build competency maps linking your topics to NMC domains (Knowledge, Skill, Attitude, Communication) and Bloom's Taxonomy levels.
Write video scripts for 10-minute recorded lectures with timestamps, narration text, and diagram prompts.
Design DOAP/OSPE stations for practical assessments.

Tip: Just type naturally. For example: "Give me a lecture on Glycolysis" or "Make 5 MCQs on Lipid Metabolism" — the tool will guide you from there.

What It Does NOT Do : Does not fact-check primary literature (use Perplexity Course Tutor for that), does not replace your final editorial judgment, does not have access to your institutional LMS.

Tutorial Video
Use this tool

Perplexity Course Tutor

Faculty Development

Faculty Development

Your 30-minute-a-day mentor for mastering AI-driven research using the Green/Yellow/Red Light Decision Tree for source trustworthiness.

Context & Instructions :
This is your personal course companion — like a senior colleague sitting beside you while you learn to use Perplexity AI for the first time.

Who is this for? Junior and senior medical faculty in India who want to use AI for teaching preparation, research, and curriculum work — but want to do it responsibly, without spreading wrong information to students.

What does this tutor do?

It walks you through a 13-day self-paced course (designed by Dr. Amol Shinde) that teaches you how to use Perplexity AI safely and confidently. The tutor is your guide — it explains concepts, asks you to reflect, helps you when you are stuck, and builds your verification habits step by step.

The core skill you will learn — the Decision Tree:

🟢 Green Light — The source is trusted (peer-reviewed journal, WHO guideline, NMC document, ICMR data). Safe to use and cite in your lectures.
🟡 Yellow Light — The information looks correct but is not fully verified. Cross-check with one more source before using in class.
🔴 Red Light — The source is unreliable, the link is broken, or the AI has invented a fake reference. Reject immediately. Do not use.
How is the course structured?

Course Structure( Can be updated if required): Three-Unit Progression
The tutor follows a Module 1 → Module 2 → Week 3 progression across 13 days:

Module 1: Foundations (Days 1–5)
Day 1 — Your first 3 Perplexity queries, using the Decision Tree to set trust expectations before reading results.
Day 2 — Running queries on a real teaching task you owe this week; categorising outputs as useful vs. weak; identifying your best query pattern.
Day 3 — Side-by-side Perplexity vs. Google comparison, timed, assessing speed vs. verifiability separately.
Day 4 — Failure Testing — the most important day of Module 1. You run 5 queries designed to break Perplexity (niche Indian data, clinical decisions, obscure journals, no-single-answer questions, last-7-day data). You document each failure mode.
Day 5 — Use-Case Map. Synthesise Days 1–4 into 5+ green-light and 5+ red-light cases on one page.

Module 2: Reliable Practice (Days 6–10)
Confronting the 5 common fears medical faculty hold about AI ("Will it replace me?", "Students will cheat," "If it cites sources it must be accurate," etc.) with evidence-based reframes from the Myth-Busting Chart.
Learning the 3-Check Method for verifying every citation (Check 1: Does the source exist? Check 2: Does it actually say what Perplexity claims? Check 3: Is it credible for this use?).
First structured verification practice on real citations.
Advanced prompting to get better research results.

Week 3: Application (Days 11–13)
Capstone project — creating a real, verified teaching deliverable you will actually use (lecture material, student handout, assessment, etc.).
Applying the full workflow: query → verify → add your teaching layer → document with an AI Use Statement.
Verification Day — applying the 3-Check Method to every citation in your Capstone.
Drafting a Student AI-Search Policy and preparing a colleague demo.
Day 13 — completing the Capstone with self-assessment, AI Tutor hybrid review, and a closing reflection on independence.

How does the tutor behave?

It is a mentor, not a search engine.

The goal: By Day 13, you should be able to say "I do not need the Tutor anymore — I have the habits now." That is the tutor's highest success.

What It Does NOT Do : Does not run Perplexity searches for you (you must use Perplexity directly), does not replace reading the full primary source, does not certify CME credit.

Tutorial Video
Use this tool