Unavailable

This livestream is restricted

Already a member? Login with your membership email address

The Fifth Elephant 2024 Annual Conference (12th &13th July)

Maximising the Potential of Data — Discussions around data science, machine learning & AI

This video is for members only

Yuvraj Gagneja

@ygagneja

Scaling Customer Delight at Zomato using AI

Submitted May 15, 2024

Introduction

In today’s rapidly evolving digital landscape, Generative AI is playing a pivotal role in transforming how our businesses interact with the customers.

GenAI is being leveraged to solve a variety of use-cases innovatively at Zomato and Blinkit - Recipe Rover, Zomato AI, People Co-pilot, Logs Co-pilot, and Customer Delight (ZIA).

This talk will focus on the journey of Gen AI in scaling Customer Delight at Zomato.

Target Audience

The primary audience for this talk includes anyone interested in Gen AI applications at scale - AI researchers, developers, engineers, product and business leaders.

Outline For Customer Delight Solution Deep Dive

  • Problems with old flow
    • Feels transactional and pre-defined
    • Unable to decipher intent and actual issue faced by the customer
  • Requirements of a solution
    • Feel conversational and generate contextual replies
    • Understand the intent and issue and provide resolutions accordingly
    • Escalate to a human agent when unable to provide resolution
  • Prime metrics to track success of the solution
    • CSAT scores
    • Escalation %
    • Cost and Latency
  • AI Solution Design
    • Explanation and reasoning behind chosen architecture
    • Marrying linguistic variables with code - policies
    • Some other optimisations
    • Evaluation pipeline for staying on top
  • Next Steps
    • Optimizing for control, cost, latency
    • Personalisation for customer love
    • Automating post order delivery delight
    • Expand to Blinkit

Outline For System Design to Enable AI Customer Delight at Scale

  • Agent Orchestrator Service
  • Internal AI Interfaces Demo
  • Internal LLM Evaluation Toolkit

Key Takeaways

  • Building and scaling GenAI systems for real-world applications (Mother’s day performance of the bot)
  • Transforming traditional customer support from transactional to conversational
  • Integrating linguistic models with business policies to implement guardrails in AI systems
  • Evaluation pipeline for a constant feedback loop

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jump starting better data engineering and AI futures

Supported by

Gold Sponsor

Atlassian unleashes the potential of every team. Our agile & DevOps, IT service management and work management software helps teams organize, discuss, and compl

Silver Sponsor

Together, we can build for everyone.

Workshop sponsor

Datastax, the real-time AI Company.

Lanyard Sponsor

We reimagine the way the world moves for the better.

Sponsor

MonsterAPI is an easy and cost-effective GenAI computing platform designed for developers to quickly fine-tune, evaluate and deploy LLMs for businesses.

Community Partner

FOSS United is a non-profit foundation that aims at promoting and strengthening the Free and Open Source Software (FOSS) ecosystem in India. more

Beverage Partner

BONOMI is a ready to drink beverage brand based out of Bangalore. Our first segment into the beverage category is ready to drink cold brew coffee.