Member story · Cohort 08 · August 2026

Acquisition and onboarding. AI in the daily work, the right balance

Assistant Product Manager at American Express in Delhi, on the digital acquisition and onboarding journeys new customers take. An MBA at FMS Delhi, consulting at EY and growth at CATKing Educare before that.

Poorvi’s portfolio

Poorvi Nigam Assistant Product Manager at American Express

Poorvi’s feedback

In Poorvi’s own words

What Poorvi wrote about the course after Cohort 08. These are real people with real portfolios, not marketing copy. Want to talk to Poorvi? I’ll intro you.

Poorvi NigamCohort 08 · August 2026

Poorvi on the course

I found the 8 weekends really helpful! There’s a lot out there that can confuse and overwhelm anyone easily.

I was looking for something structured, touching on not just fundamentals but hands-on sessions, to see how a PM can effectively bring AI into their daily work while keeping it relevant and helping their product evolve at par with the industry. These 8 weekends provided that right balance.

Additionally, the community that has been built is worth being a part of. I would definitely be recommending this to my fellow PMs.

Thanks again for all the knowledge you guys shared!

✓✓

What changed for Poorvi

Fundamentals and hands-on, the right balance.

AI in the daily work of a PM.

A community worth being part of.

Poorvi learned alongside PMs from

The path

Growth, consulting, an MBA, then product

2020
Project Manager
CATKing Educare
2022
Consulting Intern
EY
2023
Associate, Digital Acquisition
American Express
2025
Assistant Product Manager
American Express
Aug 2026
Curious PM
Cohort 08, August 2026

The work

What Poorvi built, and writes

See everything on Poorvi’s portfolio ↗

01 / 04

Database-connected AI chatbot with evals

A chatbot built in five stages, from a plain OpenAI call to one with conversation memory, tools and a live database behind it, then every answer traced in Langfuse and scored by AI judges.

OpenAI Streamlit PostgreSQL Langfuse

Open ↗

What it teaches a PM

Memory was the smallest change with the largest effect; evals made the answers measurable.

02 / 04

Podcast search engine and MCP server

Semantic search over a thousand podcast episodes, then the same engine exposed over the Model Context Protocol so an AI assistant can search, keep notes and run research briefs.

MCP RAG Pinecone FastMCP

Open ↗

What it teaches a PM

An MCP endpoint is a live API: ship it with auth.

03 / 04

Podcast RAG and fine-tuning

Question answering over 149 podcast transcripts, whole episodes and 900-character chunks side by side, then a small open model fine-tuned with LoRA to speak in a chosen persona.

RAG Pinecone Claude Fine-Tuning

Open ↗

What it teaches a PM

Retrieval for facts the model has never seen, fine-tuning for how it speaks.

04 / 04

Personal AI agent with voice

One agent loop that searches and reads the web, remembers you between sessions, runs a job search from your resume and answers the phone, with chat and voice sharing one memory.

AI Agents mem0 ElevenLabs Twilio

Open ↗

What it teaches a PM

The assistant grows by registering tools, not by adding branches.

What Poorvi writes

poorvi.curious.pm4 min read ↗

Test the Idea Before You Build It

A/B tests on acquisition and onboarding journeys to check a hypothesis before the full feature is built: the habit sounds obvious, doing it well takes discipline.

poorvi.curious.pm3 min read ↗

Compliance Is Part of the Onboarding Experience

Collecting what regulations require from a new financial services customer, in a way that keeps the experience good: compliance and customer experience are not opposite sides.

poorvi.curious.pm3 min read ↗

Start Product Work With Research, Not Features

Life science, digital marketing, consulting and an MBA, with one common thread: understanding a market, a customer or a sales network before deciding what to change.

Around Poorvi