Enterprise Knowledge Search · Marketing Personalization
Riversoft needed a better way to support semantic travel search and automated travel product matching because its first-generation travel AI delivered slow inference, weak relevance, and too much manual effort when matching traveler requests to packages.
Reported impact
Riversoft improved semantic travel search and automated travel product matching with measurable results including Riversoft Reduces Inferencing Time for Smart Travel System by 75% with Generative AI on AWS, reduction in inferencing time, from 20 to 5 seconds, and 75% lower costs for hosting llms, while giving teams a faster path from governed data to production decisions.
Riversoft uses Serverless compute and Amazon Bedrock to support semantic travel search and automated travel product matching. The implementation replaced a legacy state where its first-generation travel AI delivered slow inference, weak relevance, and too much manual effort when matching traveler requests to packages. Travel catalog content and customer travel queries move through AWS Lambda and land in shared lakehouse datasets, giving teams one trusted data foundation. Central governance keeps access, lineage, and compliance consistent across downstream teams. Serverless compute, Amazon Bedrock, and Amazon SageMaker operationalize models, agents, and analytics that deliver semantic travel matches and itinerary and package recommendations.
Travel catalog content and customer travel queries land on a shared platform, pipeline services clean and standardize them, governance controls enforce trusted access, and AI, model-serving, and analytics services deliver semantic travel matches and itinerary and package recommendations.
The support we received from AWS in deploying models on Amazon SageMaker made the learning curve much faster and more efficient than trying to work things out on our own,
We need reliable NER models to help our system identify domain-specific terms or word combinations a customer may type and how those are related to available travel offerings.
We use BERT models for diverse activities such as named entity recognition and document classification,
When we were using our previous AI provider, we couldn’t solve the problem. But when we started testing Claude models on AWS, we realized that Claude’s logical reasoning abilities are stronger.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Jul 26, 2024 Daxte To develop AI models for its solution, the company fine-tuned open-source large language models such as Llama2 7b from Hugging Face with its own datasets and used Amazon SageMaker , a fully managed service that brings… Improving Performance Using AWS As of December 2023, LegalMap had a dataset of nearly 125 million documents… Amazon SageMaker 
Databricks Sample Jul 21, 2026 Zapier Zapier needed a better way to support AI-powered self-service analytics, conversational data access, and product personalization because legacy data silos and reliance on a central insights team meant many questions… 2–3 hours delivering ai-powered product and business insights Agent Bricks · Databricks Data + AI Platform · MLflow Databricks Sample Apr 1, 2026 Workday Workday needed a governed, AI-ready data foundation that could serve every line of business — from product telemetry and sales analytics to AI-driven marketing — and let technical and non-technical teams alike build… Every business unit launched sandbox workspaces in 6 months Databricks Data Intelligence Platform · Unity Catalog 