Security rules barred LLMs from their data warehouse. A vault encrypted credentials on the fly; 5,000 now query petabytes in plain English.
A global payments platform operating in nearly 200 markets, managing a data estate spanning petabytes with billions to trillions of records in BigQuery.
To enable 5,000 employees to query data in plain English, PayPal needed to connect LLMs to their data warehouse, but standard conversational AI...
“The real win here was delivering conversational analytics to 5,000 employees, fully secured and governed, by extending what we already had. No migrations, no rewrites, just smart architecture on top of Looker's semantic layer. That's how PayPal innovates at scale.”
Digital payment platform and mobile wallet for consumers and businesses.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
PayPal's Conversational analytics is part of this use case:
Related implementations across industries and use cases
Client analytics required SQL queries only engineers could write. Now CSMs pull performance reports in minutes with plain language prompts.
Every session, sellers and analysts started from zero—explaining Stripe to AI that had never heard of it. Kai already knows the company.
15 data domains, 20-minute queries, some tables too large to touch. One hackathon later, AI fields half of all queries—customers included.
Client analytics required SQL queries only engineers could write. Now CSMs pull performance reports in minutes with plain language prompts.
15 data domains, 20-minute queries, some tables too large to touch. One hackathon later, AI fields half of all queries—customers included.
Analysts couldn't touch the data—every question funneled through engineers, taking hours or weeks. Now they get answers in seconds.
Finance spent six hours stitching four data sources into fully burdened cost models. Now, they use AI to generate them in minutes.
Manual document summaries bottlenecked experienced staff. Now, AI drafts preliminary risk assessments, freeing teams for complex advisory.
Multilingual expansion meant days-long vendor queues and manual file conversions. DeepL solved both, cutting turnaround by more than half.
Security rules barred LLMs from their data warehouse. A vault encrypted credentials on the fly; 5,000 now query petabytes in plain English.
A global payments platform operating in nearly 200 markets, managing a data estate spanning petabytes with billions to trillions of records in BigQuery.
To enable 5,000 employees to query data in plain English, PayPal needed to connect LLMs to their data warehouse, but standard conversational AI...
“The real win here was delivering conversational analytics to 5,000 employees, fully secured and governed, by extending what we already had. No migrations, no rewrites, just smart architecture on top of Looker's semantic layer. That's how PayPal innovates at scale.”
Digital payment platform and mobile wallet for consumers and businesses.
Cloud computing services, AI infrastructure, and data analytics platforms for enterprises.
PayPal's Conversational analytics is part of this use case:
Related implementations across industries and use cases
Client analytics required SQL queries only engineers could write. Now CSMs pull performance reports in minutes with plain language prompts.
Every session, sellers and analysts started from zero—explaining Stripe to AI that had never heard of it. Kai already knows the company.
15 data domains, 20-minute queries, some tables too large to touch. One hackathon later, AI fields half of all queries—customers included.
Client analytics required SQL queries only engineers could write. Now CSMs pull performance reports in minutes with plain language prompts.
15 data domains, 20-minute queries, some tables too large to touch. One hackathon later, AI fields half of all queries—customers included.
Analysts couldn't touch the data—every question funneled through engineers, taking hours or weeks. Now they get answers in seconds.
Finance spent six hours stitching four data sources into fully burdened cost models. Now, they use AI to generate them in minutes.
Manual document summaries bottlenecked experienced staff. Now, AI drafts preliminary risk assessments, freeing teams for complex advisory.
Multilingual expansion meant days-long vendor queues and manual file conversions. DeepL solved both, cutting turnaround by more than half.