Lloyds Banking Group Built Envoy with Gemini Enterprise
Read the Portuguese translation →
Author: Google Cloud · Watch on YouTube
Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.
Original language: English
Original video: Lloyds Banking Group Built Envoy with Gemini Enterprise · Channel: Google Cloud · 02:21 · Watch on YouTube
Topics: AI agents, Enterprise AI applications, AI governance and regulation, AI infrastructure and hardware
Summary
Section titled “Summary”Lloyds Banking Group is applying AI across 12 major areas, including investment services, fraud management, and commercial-bank onboarding. Its Envoy platform, built in collaboration with Google Cloud and based on Gemini Enterprise, provides a secure, managed path for bringing agentic AI use cases into production. Envoy offers reusable agents, engineering tools, guardrails, and a Golden Path with scaffolding and a CI/CD pipeline. The group emphasizes privacy and security, particularly in a regulated industry, and sees agentic AI as an important way to help detect and manage fraud.
Key points
Section titled “Key points”- Lloyds Banking Group is applying AI across 12 major areas of its business.
- Envoy is the bank’s pipeline for securely bringing agentic use cases into production.
- Envoy is based on Gemini Enterprise and was developed in collaboration with Google Cloud.
- Nearly 1,000 engineers have been onboarded to work on agentic use cases using Envoy.
- A marketplace lets teams reuse agents built by other teams across the bank.
- Envoy provides tooling, a foundation, and guardrails so teams can focus on adding value in individual use cases.
- The Golden Path offers scaffolding for designing and building agent applications, followed by a CI/CD pipeline.
- The bank is exploring Google Cloud security features to support data privacy and security.
- Agent use cases can help detect and manage potential fraud and save time for customers.
Chapters
Section titled “Chapters”| Start | Chapter | Summary |
|---|---|---|
| 00:10 | Lloyds’ AI ambitions | Ron van Kemenade describes the bank’s goals and its 12 major AI initiatives. |
| 00:44 | Introducing Envoy | He explains how Envoy, built with Gemini Enterprise and Google Cloud, securely brings agentic use cases into production. |
| 01:15 | Reusable agents and the Golden Path | Envoy supports agent reuse across teams and provides tooling, guardrails, scaffolding, and a CI/CD pipeline. |
| 01:48 | Security, fraud, and the future | The video highlights data security, fraud-management use cases, and the importance of guardrails in a regulated industry. |
Quotes
Section titled “Quotes”AI is substantially going to change the way we do business with our customers. — 00:10
Envoy is our pipeline to bring agentic use cases in a secure and safe way, fully managed into production. — 00:44
Data privacy and data security are at the heart of what banks do. — 01:48
everything is moving agentic AI. — 02:21
Concepts and entities
Section titled “Concepts and entities”Lloyds Banking Group, Ron van Kemenade, Envoy, Gemini Enterprise, Google Cloud, Golden Path, CI/CD pipeline, Agentic AI
Full transcript (original language)
Section titled “Full transcript (original language)”00:10 AI is substantially going to change the way we do business with our customers. My name is Ron van Kemenade. I’m the Group Chief Operating Officer for Lloyds Banking Group. Our big objective is to help companies, individuals, and communities prosper all across the United Kingdom. We are applying AI in 12 big bets that range from our proposition in investments to fraud management or onboarding clients for the commercial bank.
00:44 Envoy is our pipeline to bring agentic use cases in a secure and safe way, fully managed into production. It’s based on Gemini Enterprise,so a full collaboration with Google Cloud. Gemini Enterprise helps us offer a solid foundation to all of our engineers building use cases. And so far, we have onboarded close to 1,000 engineers working on agentic use cases making use of Envoy. So you said you had a use case team that was
01:15 looking for an orchestrator agent. You could send them to the marketplace where we have a number of different agents that have already been built that can then be reused by other teams across the bank. We invested together with Google Cloud into this tooling that helps us create a foundation, create a harness, provide guardrails, to make sure that we focus on adding value in the individual use cases. One of the core components of Envoy is the Golden Path. That gives our users some scaffolding of how they would design
01:48 and build their agent application, and then essentially a CI/CD pipeline. Data privacy and data security is at the heart of what banks do. With Envoy, we have a roadmap to better make use of the security features of Google Cloud. Both the bank as well as our customers benefit from a use case for our agents to better detect and manage potential fraud. It saves a lot of time for them to help customers go through such a difficult situation. All of this is extremely relevant in a highly
02:21 regulated industry,and that’s where an agentic AI pipeline, including all the guardrails and security, play such an important role. What the future will look like,it’s hard to predict, but from what I can tell today, everything is moving agentic AI.