Reported impact
Business outcome
reduced from 13 minutes to 2 minutes Catalog; 10% online search growth expectation
- Productivity Improvement
AWSRetailAI and Machine LearningCost OptimizationCybersecurityGenerative AI / LLMProductivity Improvement2023 AWSAWS#ff9900RetailBrazilGimba is a Brazilian retail and supply chain leader, responsible for the chains of 300 of the 500 largest companies in Brazil, scheduling all deliveries, quality standards, and defining SLAs for restocking.10% online search growth expectationJan 1, 20236Amazon Bedrock · Amazon SageMaker0 2023-01-01 6
Gimba
Gimba is a Brazilian retail and supply chain leader, responsible for the chains of 300 of the 500 largest companies in Brazil, scheduling all deliveries, quality standards, and defining SLAs for restocking.
10% online search growth expectation
13 minutes
2 minutes
reduced from 13 minutes to 2 minutes Catalog
Solution
Gimba is a Brazilian retail and supply chain leader, responsible for the chains of 300 of the 500 largest companies in Brazil, scheduling all deliveries, quality standards, and defining SLAs for restocking. Key services included Amazon Bedrock hosts the foundation models and generative ai application logic; Amazon SageMaker supports model training, tuning, deployment, or managed ml inference. reduced from 13 minutes to 2 minutes Catalog; 10% online search growth expectation # Gimba adopts generative AI on AWS to enhance its product catalog The developed platform replaces the manual maintenance process for the catalog, which today has about 30,000 items, and reduces product registration time by 84%.
Solution architecture
- Compute
- Amazon Bedrock Hosts the foundation models and generative AI application logic.
- Amazon SageMaker Supports model training, tuning, deployment, or managed ML inference.
Evidence from the source
10% online search growth expectation
Gimba CTO (Chief Technology Officer), Daniel Arruda, explains that catalog updates were performed manually until now, for all of the circa 300 new products included monthly.
Gimba is a Brazilian retail and supply chain leader, responsible for the chains of 300 of the 500 largest companies in Brazil, scheduling all deliveries, quality standards, and defining SLAs for restocking.
With support from AWS and Flexa Cloud - an AWS partner that uses Generative Artificial Intelligence (AI)-, Gimba developed a platform to automate the steps involved in building its product catalog, which contains about 3
reduced from 13 minutes to 2 minutes Catalog
“Each manufacturer sends us their product data in different formats and we have several collaborators who read and standardize this data, creating product descriptions in our catalog, especially the online one,” he expla
Transparency Evidence & methodology
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 value76/100
- Problem clarity20/20Measures whether the customer's operational problem is specific enough to compare.
- Implementation depth10/25Rewards named components, data flow, integrations, and architecture detail.
- Outcome specificity16/20Measures whether the reported benefit is concrete rather than a generic claim.
- Quantified impact25/254 metrics describe measurable impact.
- Deployment scale5/10Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence85%
- Source authority20/25The main evidence is an official vendor-published customer story.
- Claim traceability21/2510 of 12 key fields link to a named source.
- Direct evidence20/206 direct source quotes retained.
- Date provenance8/10The publication date comes from publisher-controlled metadata.
- Source transparency8/101 source reference document publisher, URL, authority, retrieval, and supported fields.
- Implementation specificity8/10Rewards 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.
- https://aws.amazon.com/solutions/case-studies/gimba-case-studyAWSFirst-party
Gimba 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
- Publication date
Date evidence
- Publisher catalog date Jan 1, 2023 · AWS · First-partyOpen date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.
Related
Similar use cases
AWS Sample Feb 28, 2025 Migros One On the journey of growing its business and optimizing operations, Migros One wanted its small engineering team to focus on accelerating innovation and delivering customer value quickly rather than on operations. The… 1 million+ AWS Glue · Amazon Bedrock · Amazon Bedrock Knowledge Bases AWS Sample Feb 25, 2025 Tapestry As part of its digital-transformation journey, Tapestry has embraced a bold approach to implementing generative AI across its enterprise. Wanting to start with an internal solution before expanding to public… Amazon Bedrock · Amazon Titan · Claude 3 Haiku AWS Sample Feb 20, 2025 Saks Founded in 1924, Saks Fifth Avenue is famous for luxury brick-and-mortar stores that offer a wide selection of premier clothing and accessories. Key metrics per interaction saved on after-call work 15 seconds with a few sentences Summarize a 20-minute call… Amazon Bedrock · Amazon Connect · Amazon Transcribe