i-Tom Solutions Scales Customer Support for Romanian SMBs with a Generative AI Assistant on Amazon Bedrock
Romanian SaaS invoicing provider i-Tom Solutions, which serves over 170,000 SMBs through its FGO platform, worked with AWS Partner Auvaria to build a retrieval-augmented generation support assistant on Amazon Bedrock, using AWS Lambda for document processing and Amazon OpenSearch Service for semantic search. After a 4-5 week proof of concept, the assistant went from POC to live production deployment in one week and now handles hundreds of customer inquiries per day, including out-of-hours queries, without expanding the human support team.
Overview
Romanian SaaS invoicing provider i-Tom Solutions, which serves over 170,000 SMBs through its FGO platform, worked with AWS Partner Auvaria to build a retrieval-augmented generation support assistant on Amazon Bedrock, using AWS Lambda for document processing and Amazon OpenSearch Service for semantic search. After a 4-5 week proof of concept, the assistant went from POC to live production deployment in one week and now handles hundreds of customer inquiries per day, including out-of-hours queries, without expanding the human support team.
This entry has 14 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
As customer inquiries surged to 600 per day, i-Tom Solutions needed to maintain fast, accurate support for its FGO invoicing platform without expanding its human support team; prior attempts to build an intelligent virtual assistant had not yielded a production-ready platform.
The solution
i-Tom Solutions worked with AWS solutions architects and AWS Partner Auvaria to build a retrieval-augmented generation agent on Amazon Bedrock that answers customer questions by drawing from the company's centralized knowledge base, using AWS Lambda for document processing and Amazon OpenSearch Service for semantic search, deploying the validated architecture to production using infrastructure-as-code templates after a 4-5 week proof of concept.
Reported business value
The generative AI assistant moved from a 4-5 week proof of concept to live production deployment in just one week, and now manages hundreds of customer inquiries each day, including out-of-hours queries, reducing pressure on the FGO support team without expanding headcount.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other technology & software entries in the register.
HP crafts marketing campaigns that resonate with customers using Databricks and Uniphore
HP centralized first-party customer data on the Databricks Data + AI Platform with Delta Lake and Unity Catalog, and connected it to Uniphore's HybridCompute for federated query pushdown, cutting campaign setup from 2 weeks to 2 hours and processing 400 million records in seconds.
Building a safer and more sustainable world
Novade, a construction management software company, partnered with Databricks to modernize its analytics and ML infrastructure, moving from a homegrown Apache Airflow stack to the Databricks Data + AI Platform with Delta Lake, Unity Catalog and MLflow. The move reduced total cost of ownership by 60% and supported a 100% increase in new clients, while enabling ML models for predicting incident risk affecting worker safety and project delivery schedules.
SafeGraph optimizes geospatial data processing with Databricks and Delta Sharing
SafeGraph used the Databricks Data + AI Platform, Delta Lake, Delta Sharing and MLflow to process petabytes of geospatial data and feed predictive models, achieving 2x-10x faster spatial querying, indexing and partitioning and a 50% reduction in peak memory consumption compared to other platforms, while reducing data access time for partners from months to minutes via Delta Sharing.
Transforming Weather Forecasting with Lakeflow Jobs
AccuWeather migrated from on-premises infrastructure to Databricks and Lakeflow Jobs, working with Datadog for observability, to unify diverse weather data formats and orchestrate 4,500+ weekly jobs. Lakeflow Jobs coordinates the ingestion of multiple weather models, triggers machine learning processes that weight and blend different forecasts, and manages complex job dependencies for reinforcement training workflows used in AccuWeather's proprietary forecasting engine. AccuWeather reports 3x faster dataset development (three months to one month per dataset), a 50% reduction in unactionable alerts, and 50% cost savings on serverless job usage.
AccuWeatherLakeflow Jobs · Delta Sharing · DatadogWas this helpful?
Your feedback helps us improve our use case database