Google Cloud Financial Services United States

KeyBank

Application Refactoring

Yet, as the bank scaled its cloud presence, a new bottleneck emerged.

Read the original story Explore all use cases

680 hours of manual work completed in 13 hours by automating tasks with Gemini CLI

Gemini CLI has now become indispensable for daily development work. Steinbrenner uses it to analyze code sections and automatically generate standardized task formats for his developers, providing a clear overview of the work required…

How do you build on more than 200 years of banking expertise to power a digital-first future? For KeyBank , an American financial institution that operates approximately 950 branches and 1,200 ATMs across 15 states, technology has long…

KeyBank's pilot of Gemini CLI cut a three-month project to five days and saved 680+ hours of manual coding work.

Reported impact

Business outcome

680 hours of manual work completed in 13 hours by automating tasks with Gemini CLI; Five days to build complex Java meta-framework instead of three months; KeyBank's pilot of Gemini CLI cut a three-month project to five days and saved 680+ hours of manual coding work.

Solution

Yet, as the bank scaled its cloud presence, a new bottleneck emerged. To kick off the POC, KeyBank integrated Gemini CLI into daily developer workflows to tackle everything from routine documentation to high-stakes legacy migrations. As part of this effort, Steinbrenner used CLI to build a complex Java meta-framework to… Beyond raw speed, Gemini CLI improved the quality and clarity of the development process by serving as a first reviewer for the team. Previously, reviewing large code branches could take a full day, but Gemini now summarizes changes across branches,… Key components include Gemini CLI provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis. Reported outcomes include 680 hours of manual work completed in 13 hours by automating tasks with Gemini CLI; Five days to build complex Java meta-framework instead of three months; KeyBank's pilot of Gemini CLI cut a three-month project to five days and saved 680+.

Solution architecture

1 components · 1 layer

Compute
- Gemini CLI Provides the reasoning or generation layer used for classification, orchestration, content generation, or analysis.

Architecture clues

Starting in 2018, KeyBank shifted its data warehouse and fintech acquisitions to Google Cloud , a move that reduced costs and bolstered security while establishing a flexible foundation for growth. Yet, as the bank…
To kick off the POC, KeyBank integrated Gemini CLI into daily developer workflows to tackle everything from routine documentation to high-stakes legacy migrations. As part of this effort, Steinbrenner used CLI to build…

Evidence from the source

680 hours of manual work completed in 13 hours by automating tasks with Gemini CLI

How do you build on more than 200 years of banking expertise to power a digital-first future? For KeyBank , an American financial institution that operates approximately 950 branches and 1,200 ATMs across 15 states,…

KeyBank's pilot of Gemini CLI cut a three-month project to five days and saved 680+ hours of manual coding work.

Starting in 2018, KeyBank shifted its data warehouse and fintech acquisitions to Google Cloud , a move that reduced costs and bolstered security while establishing a flexible foundation for growth. Yet, as the bank…

To kick off the POC, KeyBank integrated Gemini CLI into daily developer workflows to tackle everything from routine documentation to high-stakes legacy migrations. As part of this effort, Steinbrenner used CLI to build…

“We saw an opportunity to use generative AI to standardize coding processes and alleviate the mental load on developers,” says Joseph Steinbrenner, technical lead for KeyBank’s Card Technology Engineering team. Building…

Transparency Evidence & methodology 72/100 reference value · 77% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value72/100

Problem clarity12/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth15/25
Rewards named components, data flow, integrations, and architecture detail.
Outcome specificity20/20
Measures whether the reported benefit is concrete rather than a generic claim.
Quantified impact25/25
3 metrics describe measurable impact.
Deployment scale0/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.

Evidence confidence77%

Source authority20/25
The main evidence is an official vendor-published customer story.
Claim traceability21/25
10 of 12 key fields link to a named source.
Direct evidence20/20
6 direct source quotes retained.
Date provenance0/10
The publication date has no documented provenance.
Source transparency8/10
1 source reference document publisher, URL, authority, retrieval, and supported fields.
Implementation specificity8/10
Rewards source-backed components, data flow, quantified impact, and a specific outcome.

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

Google Cloud
KeyBank customer story

First-party
https://cloud.google.com/customers/keybank

Source type
Vendor-published customer story
Supports
- Customer
- Business problem
- Solution
- Products
- Solution components
- Data flow
- Integrations
- technical area
- use case category
- Business outcome
- outcome category
- Metrics
- Architecture
- evidence quotes

Date evidence

First archived Aug 25, 2026 · Internet Archive · Independent First Wayback Machine capture; confirms the page existed by this date, not when it was published.
Open date source
Sitemap last modified Aug 24, 2026 · Google Cloud · Publisher metadata Publisher-reported modification timestamp; not a publication date.
Open date source

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Similar use cases

See all like this

Google Cloud Archived · Aug 29, 2026 PayPal Financial Services United States After unifying its core data estate, PayPal needed an AI platform that could power global commerce use cases, let developers choose the best model for each workload, and elastically handle training and inference without… 25,000 pipelines every day Application RefactoringIT Operations Automation BigQuery · Cloud GPUs · Gemini Enterprise Agent Platform

Google Cloud Archived · Apr 28, 2026 CME Group Financial Services United States CME Group the world’s leading derivatives marketplace, has built an enviable reputation for trust and reliability over its 175-year history. However, driven by a culture of innovation, it isn’t resting on its legacy and… 10+ hours of monthly productivity gains per developer Application RefactoringSystem Migration Antigravity · Gemini CLI · Gemini Code Assist

Google Cloud Modified · Oct 9, 2026 Porter Logistics India Porter (Smartshift Logistics Private Limited), a leading logistics platform based in India, orchestrates on-demand mini-trucks, tempos, and two-wheelers across 50+ major cities. When order volumes doubled, Porter’s… Achieved 30% zero-touch driver verification automation on Gemini platform Application RefactoringDocument Processing BigQuery · Cloud Composer · Cloud Pub/Sub