KP / Product
Krishna Paruchuri — Senior Product Manager
— Currently
Senior Product Manager
16+ years building products
Krishna Paruchuri

Senior Product Manager
at the intersection of
healthcare, fintech
& agentic AI.

Sixteen years translating ambiguous problems into shipped products — eleven in healthcare, five in fintech, and now actively building at the agentic AI frontier.

Explore work in healthcare, fintech & AI
01 — About

A bridge between
strategy & system.

Eleven years building healthcare products — hospitals, EHR / EMR systems, payer platforms, claims, and quality systems — at companies including Napier Healthcare and IBM Watson Health. Five years in fintech and identity, at Reliance Jio and now Experian. Today I work at the intersection of all three: agentic AI for regulated domains, fraud detection and identity verification, and the quiet plumbing of enterprise B2B platforms.

I bridge business strategy and technical architecture — translating ambiguous problems into shipped products that move metrics.

"A clean, intuitive UI should seamlessly mask substantial engineering complexity."
Healthcare EHR / EMR·Payer & Claims·Fraud Detection·Identity Verification·Agentic AI·Fintech B2B·Enterprise Product Management
02 — Core Competencies

Core Product
Competencies.

/01Healthcare Product
/02EHR / EMR · Payer & Claims
/03Product Architecture
/04Agentic AI & RAG
/05Fraud Detection & Identity
/06Fintech & Enterprise B2B
03 — Selected Work

Shipped products &
AI experiments.

Independent Build · In Production
Operations & Finance Portal · Live deployment

TPSS Security —
Operations
& Finance Portal.

A production operations and finance portal for a manpower-security business, replacing a multi-spreadsheet workflow with a single auditable system. Built independently in my own time for a real services business — currently live in production, running monthly paysheet cycles, GST-compliant invoicing, and PF/ESI compliance workflows across 8 functional modules.

Functional surface area
01Masters & Deployments
02Payroll & Approvals
03GST Billing
04Receivables & Cash
05Statutory Compliance
06Reports & Dashboards
07User & Permission Admin
08Scheduled Jobs

Two surfaces from one codebase — a public marketing site for prospective clients, and a private role-aware operations portal for the leadership, operations, and finance teams. The portal enforces a maker–checker workflow where approved paysheets, issued invoices, and recorded receipts become immutable server-side. Historical numbers cannot drift.

Three roles. A per-screen, per-action permission grid an administrator can toggle without developer involvement. Authoritative rules enforced in the database, not the UI. Scheduled serverless jobs handle overdue-invoice sweeps, contract checks, and monthly backups.

Frontend —React 18 · TypeScript · Tailwind · shadcn/ui · TanStack Query · Recharts
Backend —Postgres · Managed auth · Serverless functions (Deno) · Object storage
Pattern —Two surfaces · One codebase · Server-enforced immutability · Scheduled jobs
Repo and screenshots intentionally private — the portal handles real client, employee, and financial data. Detail and live walkthrough available on request.
Featured Experiments
Featured Experiment
Supporting Experiments
AI · Healthcare · Full-stack prototype

MedAssist AI

MedAssist AI — Patient Details screen with an AI-generated Pre-Visit Brief summarizing the patient's clinical picture and surfacing four risk indicators
Patient details — AI pre-visit brief & risk flags
MedAssist AI — Capture Details screen with conversation input and a structured SOAP note extracted by Claude on the right
Capture details — Claude-extracted SOAP note
MedAssist AI — Claim Generation screen showing auto-generated ICD-10 codes with clinical evidence, detected coding gaps, and denial risk patterns
Claim generation — ICD-10 codes & gap detection

A Claude-powered clinical workflow application covering six phases of a patient encounter — from AI-assisted intake and appointment scheduling through to voice-transcribed SOAP notes, LOINC-mapped diagnostic orders, lab trend analysis, and auto-generated ICD-10/CPT claims. Built across two role-based portals for doctors and clinical assistants.

Stack —React 18 · Vite · Tailwind · Recharts
AI —Claude Sonnet 4.6 · Vision (OCR) · Web Speech API
Security —Cloudflare Pages Functions proxy · server-side key
Audience —Clinicians · clinical assistants · medical billing teams
Full walkthrough — patient intake → SOAP notes → diagnostics → ICD-10 claims
Fintech · Identity · Mobile MVP

FraudShield

In active development
FraudShield — Aadhaar scan screen with masked identity input and recent scan history
Scan
FraudShield — Risk result for a flagged identity with 69/100 score, AI confidence, and four detected fraud signals
Risk result
FraudShield — Case queue listing prioritized fraud cases with status and risk scores
Case queue

A mobile-first identity verification and fraud detection tool designed for India's Aadhaar-linked KYC market — banks, NBFCs, fintechs, and insurance teams. The current MVP scans for fraud signals including SIM swaps, synthetic identities, duplicate accounts, and velocity attacks, returning a 0–100 risk score in under two seconds. Designed around UIDAI masking patterns and Indian regulatory guidelines (RBI, DPDP Act).

Stack —React 18 · TypeScript · Tailwind · shadcn/ui · TanStack Query · Zod
AI —Rule-based scoring in current MVP · LLM integration in progress
Designed for —UIDAI · RBI digital lending · DPDP Act guidelines
Audience —Banks · NBFCs · Fintech · Insurance · KYC ops
MVP walkthrough — Aadhaar scan → risk score → fraud signals → case queue
04 — Contact

Building something
at the intersection of
healthcare, fintech, or AI?
Let's talk.