RetailSoftware Engineering

How Rakuten Fixes Issues 2x Faster with OpenAI Codex

Rakuten integrated OpenAI Codex into incident response, CI/CD pipelines, and autonomous development — cutting mean time to recovery by 50% and compressing quarter-long projects into weeks.

Impact

~50% reduction

Mean Time to Recovery

2x faster

Issue Resolution Speed

Quarter to weeks

Development Compression

Challenge

Needed to accelerate software delivery and incident response while maintaining security standards across a large, complex product ecosystem.

Solution

Integrated OpenAI Codex into incident response (KQL-based root cause analysis), CI/CD pipelines (automated code review and vulnerability checks), and autonomous full-stack development.

Tools & Technologies

What Leaders Say

We do not just care about generating code quickly. We care about shipping safely.

Yusuke Kaji, General Manager of AI for Business, Rakuten
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

Rakuten, a global e-commerce and fintech conglomerate with 30,000 employees, needed to accelerate software delivery and incident response while maintaining security standards across a complex product ecosystem.

The company integrated OpenAI Codex into three key operational areas: incident response using KQL-based monitoring for root-cause analysis, CI/CD pipelines for automated code review and vulnerability checks, and autonomous full-stack development from partial specifications.

Results were dramatic: mean time to recovery dropped approximately 50%, problems are fixed twice as fast, and full-stack mobile app development that previously took a quarter was compressed into weeks.

Similar Cases

CW
Camping World
40%
customer engagement increase

Camping World deployed IBM watsonx Assistant as a virtual agent named Arvee across all web properties, increasing customer engagement by 40% and improving agent efficiency by 33%.

RetailICIBM ConsultingIWIBM watsonx Assistant
E
Engine
15%
average handle time reduction

Engine, a B2B travel platform handling 500,000+ annual traveler requests, deployed an Agentforce AI agent called Eva that autonomously manages over 30% of customer cases end-to-end. The implementation reduced average handle time by 15%, lifted CSAT from 3.7 to 4.3, and delivered $2M in estimated annual cost savings — all within a 12-day deployment timeline.

RetailSASalesforce AgentforceABAgentforce Builder
S
Shopify
< 24 hours
model upgrade deployment

Shopify built Sidekick, an AI commerce assistant powered by Claude Sonnet on Google Vertex AI, enabling millions of merchants to reach their first sale in days instead of weeks.

RetailCOClaude on Vertex AIGBGoogle BigQuery
E
Etsy
~80x
listings per theme increase via algotorial curation

Etsy, the global marketplace for handcrafted and vintage goods, serves nearly 90 million buyers across more than 130 million listings from 5 million sellers. Using Vertex AI, BigQuery, Dataflow, and Gemini, the company built a personalized search and discovery platform it calls “algotorial curation” — increasing listings per theme by 80x, driving a 5% lift in SEO-driven visits, and delivering a 3% conversion improvement for sellers.

RetailGDGoogle DataflowGBGoogle BigQuery
T(
THG (The Hut Group)
60%
reduction in mean time to respond (mttr)

THG (formerly The Hut Group) is a UK-based ecommerce retail company with revenues exceeding £2 billion, selling its own-brand and third-party cosmetics, dietary supplements, and luxury goods online while also providing ecommerce infrastructure to third parties through its Ingenuity division. Facing a rapidly expanding threat surface as it grew through acquisitions and added SaaS platforms, THG deployed Elastic Security as its unified SIEM, using machine learning capabilities to surface novel attack vectors and automation to eliminate manual triage overhead. The outcome: mean time to respond to security events dropped by 60%, first-line triage burden fell from 90% to 50% of analyst time, and physical storage costs declined by 60% through intelligent data tiering.

RetailESElastic Security
M
Morrisons
98.96%
data reporting lag reduction

Morrisons, one of the UK’s largest supermarkets serving nine million customers weekly across 500 stores, migrated its on-premise data warehouse to BigQuery and Looker, reducing reporting lag by 98.96% from one day to 15 minutes. Real-time data now powers Vertex AI demand forecasting models and a customer-facing Product Finder app that receives 50,000 hits per day during peak periods.

RetailGCGoogle Cloud RunLLooker
GF
Grupo Falabella
60%
service requests resolved autonomously on whatsapp

Grupo Falabella deployed Salesforce Agentforce on WhatsApp to handle customer service for Latin America's leading retail chain, autonomously resolving 60% of service requests and growing WhatsApp channel adoption from under 50% to over 70% within three weeks.

RetailSASalesforce Agentforce
GC
Grupo Casas Bahia
14x
productivity gain in comment analysis

Grupo Casas Bahia is one of Brazil’s largest omnichannel retailers, serving over 100 million customers through more than 1,000 stores and a national logistics network. The company deployed Databricks Agent Bricks with Meta’s Llama 3.3 70B model to automate the classification of customer reviews from six distinct channels. Monthly review classification jumped from 1,500 to 33,500, model accuracy reached 90%, and the company saves over 4,000 person-hours annually — equivalent to nearly R$480,000.

RetailDUDatabricks Unity CatalogDADatabricks Agent Bricks