Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
InfoCert replaces custom ML models with Amazon Bedrock GenAI, projecting 80% lower onboarding costs
…ing, and refining measurable in terms of weeks instead of months. Additionally, InfoCert expects to reduce financial overhead by 80 percent for startup, development, and configuration costs when onboarding new customers. It also projects a 20 percent reduction in ongoing running costs for this solut…
Description
InfoCert, a European provider of trusted digital communication solutions, evolved its Intelligent Multichannel Classification and Routing (IMCR) email/document processing system into IMCR AI, replacing months-long custom ML model training with Amazon Bedrock foundation models and prompt engineering. The proof of concept achieved classification results close to the prior custom system while InfoCert projects an 80% reduction in startup, development and configuration costs and a 20% reduction in ongoing running costs when onboarding new customers.
…uting of incoming email messages and integrating with other services and tools. The new solution, IMCR AI, uses generative AI to offer a unified workflow suitable for customers with small-to-moderate information extraction needs. “By combining Amazon Bedrock’s generative models with prompt engineering, we ge…
…ing, and refining measurable in terms of weeks instead of months. Additionally, InfoCert expects to reduce financial overhead by 80 percent for startup, development, and configuration costs when onboarding new customers. It also projects a 20 percent reduction in ongoing running costs for this solut…
Company
InfoCert
…on AWS Overview As a leading provider of qualified trusted solutions in Europe, InfoCert helps companies keep their communications secure. Its Legalmail solution helps businesses verify the authenticity and legal vali…
Industry
Technology & Software
…ories InfoCert Enhances Its ML Capabilities Using Generative AI on AWS Overview As a leading provider of qualified trusted solutions in Europe, InfoCert helps companies keep their communications secure. Its Legalmail solution helps businesses verify the authenticity and legal valid…
Problem
InfoCert previously built custom ML models to classify and process emails and attachments for each Legalmail customer; training and deploying these models was a lengthy, costly process requiring months for data preparation, model training and rules definition, which limited access to larger companies.
…g (ML) integrations. InfoCert Streamlining ML Integrations Using Amazon Bedrock Previously, InfoCert built custom ML models to help classify and process emails and attachments for each Legalmail customer. Training and deploying these models was a lengthy, costly process, which limite…
Solution
InfoCert conducted a proof of concept combining Amazon Bedrock's generative foundation models with prompt engineering to evolve its Intelligent Multichannel Classification and Routing (IMCR) system into IMCR AI, offering a unified workflow suitable for customers with small-to-moderate information extraction needs, moving from a custom per-customer ML approach to a general solution requiring minimal adjustments and no model training.
…ow suitable for customers with small-to-moderate information extraction needs. “By combining Amazon Bedrock’s generative models with prompt engineering, we get preliminary results that are very close to what we achieved with the pr…
Business value
InfoCert anticipates a decrease in the time required for model definition, training and refining, measured in weeks instead of months, projects an 80% reduction in startup, development and configuration costs when onboarding new customers, and expects a 20% reduction in ongoing running costs, with preliminary classification results close to the prior custom-trained system.
…azon Bedrock, InfoCert can now integrate ML models faster and more efficiently; it anticipates a decrease in the time required for model definition, training, and refining measurable in terms of weeks instead of months. Additionally, InfoCert expects to reduce financial overhead by 80 percent for…
Technology
Amazon Bedrock
…calability of Legalmail’s features—and to make them available to more customers—InfoCert adopted generative artificial intelligence (AI) capabilities from Amazon Web Services (AWS). By using generative AI, the company is streamlining access to innovative docum…
AI capabilities
Generative AI, Document Intelligence
…bilities from Amazon Web Services (AWS). By using generative AI, the company is streamlining access to innovative document and email processing features and paving the way for more efficient machine learning (ML) integrations. InfoC…
Use case type
Document processing
…ntegrations Using Amazon Bedrock Previously, InfoCert built custom ML models to help classify and process emails and attachments for each Legalmail customer. Training and deploying these models was a lengthy, costly process, which limit…
Headline outcome
…ing, and refining measurable in terms of weeks instead of months. Additionally, InfoCert expects to reduce financial overhead by 80 percent for startup, development, and configuration costs when onboarding new customers. It also projects a 20 percent reduction in ongoing running costs for this solut…
Deployment model
cloud
…calability of Legalmail’s features—and to make them available to more customers—InfoCert adopted generative artificial intelligence (AI) capabilities from Amazon Web Services (AWS). By using generative AI, the company is streamlining access to innovative docum…
Deployment options
cloud
…calability of Legalmail’s features—and to make them available to more customers—InfoCert adopted generative artificial intelligence (AI) capabilities from Amazon Web Services (AWS). By using generative AI, the company is streamlining access to innovative docum…
