AWSSoftware / SaaSCustomer Service AutomationAI and Machine LearningContact CenterGenerative AI / LLMCost ReductionCustomer ExperienceProductivity ImprovementScalability2023AWSAWS#ff9900Software / SaaSUnited StatesAs the company continued to grow and gain new customers, it wanted to improve the availability of its solution and reduce costs. To meet its scalability, availability, and cost-optimization needs, Forethought chose to…By migrating some of its classifiers to Amazon SageMaker Serverless Inference, Forethought saved around 80…Jan 1, 20236Customer Service AutomationAmazon EKS · Amazon SageMaker · Amazon SageMaker Model Deployment02023-01-016
As the company continued to grow and gain new customers, it wanted to improve the availability of its solution and reduce costs. To meet its scalability, availability, and cost-optimization needs, Forethought chose to migrate its ML inference to Amazon SageMaker, and the company began using additional features of Amazon SageMaker to improve its products.
↗By migrating some of its classifiers to Amazon SageMaker Serverless Inference, Forethought saved around 80 percent on related cloud costs.
↗By migrating to Amazon SageMaker multi-model endpoints, we reduced our costs by up to 66% while providing better latency and better response times for customers.
↗Forethought now runs over 80 percent of its GPU inference on Amazon SageMaker between Amazon SageMaker multi-model endpoints and Amazon SageMaker Serverless Inference.
↗Using Amazon SageMaker, Forethought improved availability and customer response times and reduced its ML costs by up to 80 percent.
Reported impact
Business outcome
Forethought is continuing to grow and provide hyperpersonalized ML models for more customers. The company is still engaging AWS to improve its infrastructure and innovate its product. Key reported metrics include By migrating to Amazon SageMaker multi-model endpoints, we reduced our costs by up to 66% while providing better latency and better response times for customers.; By migrating some of its classifiers to Amazon SageMaker Serverless Inference, Forethought saved around 80 percent on related cloud costs.; Forethought now runs over 80 percent of its GPU inference on Amazon SageMaker between Amazon SageMaker multi-model endpoints and Amazon SageMaker Serverless Inference..
Cost Reduction
Customer Experience
Productivity Improvement
Scalability
Solution
Learn how Forethought Technologies, a provider of generative AI solutions for customer service, reduced costs by up to 80 percent using Amazon SageMaker. Forethought Technologies (Forethought), a customer service software provider, wanted to improve its machine learning (ML) costs and availability as it gained new customers. The company was already using Amazon Web Services (AWS) for ML model training and inference and wanted to be increasingly efficient and scalable with its small cloud infrastructure team. To achieve its goals, Forethought migrated the inference and hosting of ML models to Amazon SageMaker , which is used to build, train, and deploy ML models for virtually any use case with fully managed infrastructure, tools, and workflows. Using Amazon SageMaker, Forethought improved availability and customer response times and reduced its ML costs by up to 80 percent.
Data flow
Source data enters the Forethought Technologies workflow through its application services, processed with Amazon SageMaker, Amazon EKS, and delivered through Amazon SageMaker Serverless Inference, Amazon SageMaker Model Deployment.
Solution architecture
4 components · 2 layers
Compute
Amazon SageMakerSupports model training, fine-tuning, evaluation, or managed inference for the customer workload.
Amazon EKSRuns containerized workloads and Kubernetes-based application services.
Serving
Amazon SageMaker Serverless InferenceRuns bursty or low-footprint model inference without preprovisioned servers.
Amazon SageMaker Model DeploymentHosts production ML inference endpoints without custom infrastructure management.
Architecture clues
Because the company set up the automated pipelines for language models using Amazon SageMaker, teams at Forethought and its customers can interface with the data that they want to train and submit it.
By migrating some of its classifiers to Amazon SageMaker Serverless Inference, Forethought saved around 80 percent on related cloud costs.
Forethought’s use of Amazon SageMaker Serverless Inference revolves around small models and classifiers that are fine-tuned to each customer use case, such as automatically determining the priority of a support ticket.
Running and managing all the ML models and Kubernetes clusters was too much overhead for the small team.
“By migrating to Amazon SageMaker multi-model endpoints, we reduced our costs by up to 66 percent while providing better latency and better response times for customers.” Forethought also uses Amazon SageMaker serverless
“We are able to share resources more efficiently while providing better availability than we did in the past.” Using Amazon SageMaker, the Forethought team no longer has to worry about memory exceptions or availability,
Evidence from the source
As the company continued to grow and gain new customers, it wanted to improve the availability of its solution and reduce costs. To meet its scalability, availability, and cost-optimization needs, Forethought chose to migrate its ML inferen
By migrating some of its classifiers to Amazon SageMaker Serverless Inference, Forethought saved around 80 percent on related cloud costs.
By migrating to Amazon SageMaker multi-model endpoints, we reduced our costs by up to 66% while providing better latency and better response times for customers.
Forethought migrated its ML inference from Amazon EKS to Amazon SageMaker Model Deployment multi-model endpoints, a scalable and cost-effective solution to deploying large numbers of models.
Forethought now runs over 80 percent of its GPU inference on Amazon SageMaker between Amazon SageMaker multi-model endpoints and Amazon SageMaker Serverless Inference.
Using Amazon SageMaker, Forethought improved availability and customer response times and reduced its ML costs by up to 80 percent.
Review how this reference was scored and trace each normalized claim back to its documented source.
01
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 value95/100
Problem clarity20/20
Measures whether the customer's operational problem is specific enough to compare.
Implementation depth20/25
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
4 metrics describe measurable impact.
Deployment scale10/10
Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence87%
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 provenance8/10
The publication date comes from publisher-controlled metadata.
With your OK, we use Google Analytics cookies to see which pages and searches are useful. No ads, no profiling, and
nothing is loaded until you accept. You can change this any time under “Cookie settings” in the footer.
