Modular AI chatbot platform
A series of chatbots, each a step further: from a basic prototype to one with memory, tools and a database behind it.
What makes a chatbot useful is memory and tools, not the model alone.
Senior Product Consultant at Capgemini Invent in Bengaluru, working with retail and consumer goods clients. Product owner and business analyst at Wipro and TCS before that, and key accounts at Reliance Retail’s JioMart B2B before that.
What Rahul wrote about the course after Cohort 08. These are real people with real portfolios, not marketing copy. Want to talk to Rahul? I’ll intro you.
Loved the 8 weekends. The most striking part was building a voicebot together.
Thanks to the learnings, I got the opportunity to work on better AI initiatives in my organisation and be recognised by the leadership.
Your hook was ‘Stop nodding along & start building’, and it held: I feel more confident and understand what’s under the hood. Knowing how RAG, LLMs, embeddings, tokenisation and evals work has given me better clarity.
I still go back to the recordings and notes whenever I’m stuck.
✓✓A voicebot, built together.
Better AI initiatives, recognised by leadership.
RAG, LLMs, embeddings, evals: under the hood.
LOTS Wholesale Solutions
Reliance Retail
TCS
Wipro
Capgemini Invent
Cohort 08, August 2026
A series of chatbots, each a step further: from a basic prototype to one with memory, tools and a database behind it.
What makes a chatbot useful is memory and tools, not the model alone.
Turns podcast episodes into vector embeddings, so you can ask a question and get the answer from what was actually said.
How retrieval keeps an answer grounded in real content.
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.
The assistant grows by registering tools, not by adding branches.
Order management implementations at TCS, and years of following up on picking, packing and delivery before that: an OMS is less about software than the promises a retailer makes.
Consulting is mapping AS-IS and TO-BE processes; product ownership is writing user stories. The second job goes much better when the first is done properly.
Key accounts at LOTS Wholesale and Reliance Retail’s JioMart B2B: sales forecasts, stock and keeping B2B customers happy turned out to be good training for product.
Rahul
Sunil S Sakri
Saurav Sarkar
Prabhakar Arya A
Junisha Malkani
Shivaprasad Patil
Nishant Pandita
Sidhartha Pooboni
Raunak Pandey
Ranjith Kurukkath
Vinit Gujarathi
Pradeep Reddy
Vidhika Chakravarti
Lokesh Leel
Karine Majdalani
Guru Prasad
Every face has a story. Tap one to read it.
Eight weekends of building real AI products with a small group of PMs. You leave with a portfolio like Rahul’s.
Real testimonials, not marketing copy. Want to talk to any of them? I’ll intro you.