Document Processing
Namirial wanted to add generative AI to its digital-signing workflows without taking on the complexity of building, training, and maintaining its own AI models, while still preserving GDPR compliance and customer-data privacy.
Reported impact
Namirial built its first prototype in around 24 hours, launched the new features in preview within weeks, improved user understanding and signing speed, and saw more than 130 engineers adopt generative AI tools with a reported 35 percent productivity boost.
Namirial added generative AI to its eSignAnywhere platform by building document summarization and question-answering capabilities on Amazon Bedrock rather than training and operating its own models. Contract content from eSignAnywhere is sent to Bedrock, which powers a summarization feature for documents awaiting signature and an Intelligent Assistant that answers user questions about document content in near real time. Because Bedrock exposes multiple foundation models behind consistent APIs, Namirial could prototype quickly, compare models with minimal code changes, and move features into preview within weeks. The deployment stays within the AWS Europe (Ireland) Region and avoids using customer data for model training or fine-tuning, helping the company meet GDPR obligations while improving signing speed, comprehension, and engineering productivity.
Documents in eSignAnywhere are sent to Amazon Bedrock, which generates summaries for contracts awaiting signature and answers near-real-time questions about document content before returning the results to end users inside the signing workflow.
It helps us test different models with little or no changes to the APIs.
Namirial adopted foundation models through Amazon Bedrock to power these capabilities.
Namirial built the first prototype in around 24 hours and launched the new features in preview to test users within weeks.
Namirial developed two generative AI features for eSignAnywhere: Summarization... and Intelligent Assistant...
Over 130 Namirial engineers now use generative AI tools, and they have seen a 35 percent productivity boost.
The company also avoids using customer data to train or fine-tune its models, which keeps sensitive information private and secure.
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.
The about page states, "The Group is backed by private equity investors, Bain Capital, PSG Equity and Ambienta SGR, and has more than 1400 employees in its offices in Europe, Latin America and Asia."
Related
AWS Sample Jan 6, 2025 Smokeball While digitalization had made significant progress, the company identified that innovative law firms required more sophisticated tools to optimize operations and enhance client service. Due to challenges with… Founded in 2012, Smokeball serves over 6,000 law firms with 25,000 daily users across Australia, the UK, and… AWS Lambda · Amazon Bedrock · Amazon EKS AWS Sample Dec 8, 2024 meeting.ai # meeting.ai Optimizes Meeting Productivity with Amazon Bedrock and Claude 3 Explore how meeting.ai is revolutionizing meeting productivity Explore how meeting.ai , an innovative Indonesian startup, is leveraging the… Amazon Bedrock · Amazon Elastic Kubernetes Service · Amazon Managed Streaming for Apache Kafka AWS Sample Nov 24, 2024 GTxcel In the digital age, it comes as no surprise that printed documents are steadily declining. Once the primary method of consuming content, many of us now favor the convenience of accessing a rich array of media from a… 10 years AWS Lambda · Amazon Bedrock · Amazon S3 