Member story · Cohort 08 · August 2026

Shipped AI features already. Then, the full picture

Director of Product Management at Schmooze, the meme-based dating app, where she leads AI-native features, monetisation and growth. Edtech partnerships at Skill-Lync and business excellence at JK Lakshmi Cement before that; ISB and BITS Pilani.

Jyotsna Akurathi
Jyotsna Akurathi Director, Product Management at Schmooze
Jyotsna’s feedback

In Jyotsna’s own words

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

Jyotsna AkurathiCohort 08 · August 2026
Jyotsna on the course

Even after shipping LLM features like AI companions and a voice onboarding assistant, I found these 8 weekends filled in the full picture: an end-to-end view of AI product development, from how LLMs and agents work to the trade-offs that drive quality, efficiency and cost, and building it yourself.

✓✓
What changed for Jyotsna

The full picture, end to end.

How LLMs and agents work, and the trade-offs.

Building it yourself.

Jyotsna learned alongside PMs from
Quest American Express Publicis
Morgan Stanley Google PhonePe
Salesforce Oracle NVIDIA
Barclays Airbnb JPMorgan Chase
Microsoft Walmart Global Tech India Amazon
Cisco Palo Alto Networks Myntra
Intuit Tesco Technology Verizon
Indeed Caterpillar Unilever
Motorola Solutions Zoho Trellix
U.S. Bank Lowe's India EY
F5
The path

Construction, cement, edtech, then consumer AI

  1. 2015

    Senior Executive, Corporate PMO

    Total Environment

  2. 2019

    Manager, Business Excellence

    JK Lakshmi Cement

  3. 2021

    Lead Program Manager

    Skill-Lync

  4. 2022

    Founding PM

    Schmooze

  5. 2026

    Director, Product Management

    Schmooze

  6. Aug 2026

    Curious PM

    Cohort 08, August 2026

The work

What Jyotsna built, and writes

See everything on Jyotsna’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.

Around Jyotsna

Where Jyotsna works, and more stories

Where Jyotsna works
Jyotsna Akurathi

Director, Product Management

Since 2022 · 2 roles here
Jyotsna AkurathiJyotsna
Your turn

Jyotsna built these. What would you build?

Eight weekends of building real AI products with a small group of PMs. You leave with a portfolio like Jyotsna’s.

Next cohort
Cohort 10
Starts
February 2027
Length
8 weekends
Seats
18–24
Keep reading

More stories from the community

Real testimonials, not marketing copy. Want to talk to any of them? I’ll intro you.

All stories