Pragya
Keshap
Technical Lead / Architect
"From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud"
"From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud"
Wed May 13 - 6:50 PM EDT/New York (See in local time)
Add to Calendar
05/13/2026 6:50 PM
05/13/2026 07:00 PM
America/New_York
#WTGC2026
"From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud"
#WTGC2026
"From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud"
https://www.womentech.net/ringcentral
https://www.womentech.net/ringcentral
"From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud"
"From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud"
Don’t miss out and join visionaries, innovators, and thought leaders from all over the world at the Women in Tech Global Conference.
Vote by Sharing
Unite 100 000 Women in Tech to Drive Change with Purpose and Impact.
Do you want to see this session? Help increase the sharing count and the session visibility. Sessions with +10 votes will be available to career ticket holders.
Please note that it might take some time until your share & vote is reflected.
Session: From Docs to Dialogue: Architecting AI Chatbots for Product Discovery on Google Cloud
Most product documentation sits untouched — buried in PDFs, wikis, and portals that users never find. The real challenge is not writing better docs; it is turning them into a conversation.In this lightning talk, Pragya Keshap, Technical Architect and IEEE Senior Member, walks through the architecture of a product-aware AI chatbot built on Google Cloud — one that uses Retrieval-Augmented Generation (RAG) to ground every response in live product context rather than generic model knowledge. Drawing from enterprise API platform design and large-scale cloud-native systems, she shares how architects can connect product documentation, catalogs, and knowledge bases to Gemini via Vertex AI, AlloyDB vector search, and GKE — eliminating hallucination while enabling natural, contextual product discovery.
Attendees will leave with a practical three-layer architecture blueprint — ingest, retrieve, respond — and a clear understanding of where most chatbot implementations fail: not the model, but the grounding layer.
Because the gap between your best documentation and your user's understanding is exactly one well-designed conversation away.
Key Takeaways
- A practical three-layer blueprint — ingest, retrieve, respond — for building a product-aware AI chatbot on Google Cloud using Vertex AI, AlloyDB vector search, and GKE
Bio
Pragya Keshap is a Technical Architect and Google Developer Expert (GDE) in Google Cloud with 18 years of experience designing secure, scalable, cloud-native systems in regulated financial environments. She specializes in enterprise API modernization, AI platform architecture, zero-trust security, and conversational AI systems on Google Cloud.A published researcher and Springer Nature co-author, she contributes actively to the Google Cloud community through technical writing on InfoQ, O'Reilly Radar, and Cloud Native Now and other platforms. She is passionate about building AI systems that scale with both performance and trust.
