Real-time Analytics
Thematic needed to turn large volumes of unstructured customer feedback from multiple channels into accurate, reliable intelligence that could explain customer-experience metrics such as Net Promoter Score and help clients act on them quickly.
Reported impact
Thematic uses generative AI to transform millions of customer feedback data points into actionable customer intelligence, helping large enterprises such as Atlassian, DoorDash, and Woolworths derive more accurate and reliable insight from qualitative feedback.
Thematic uses generative AI on AWS to convert large-scale customer feedback into business intelligence for enterprise clients. Feedback from multiple channels is fed into Thematic’s analysis workflow, where the company uses Amazon Bedrock to evaluate and compare large language models and to generate curated, reliable customer-intelligence outputs. This builds on Thematic’s earlier NLP-based feedback analysis by adding a simpler way to experiment with and operationalize modern foundation models for qualitative insight generation. The platform connects themes from unstructured comments to business metrics such as Net Promoter Score and helps clients understand what is driving satisfaction or dissatisfaction at scale. With AWS, Thematic can analyze millions of feedback data points and continuously tune its approach across more than 10 LLM candidates.
Customer feedback from multiple channels is ingested into Thematic's analytics workflow, processed with Amazon Bedrock to identify themes and generate insights, and then connected back to customer-experience metrics such as Net Promoter Score.
Thematic partnered with Amazon Web Services (AWS) to use generative AI to turn customer feedback data from multiple channels into curated, accurate and reliable customer intelligence.
Using Amazon Bedrock is just so easy. Whenever we design a solution we do test more than 10 LLMs.
developed a NLP-based prototype that analyzed unstructured customer feedback, connected themes from qualitative feedback to metrics, and generated insights that explained the drivers behind the Net Promoter Score.
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 public company profile lists 'Employees 32' with 'Oct 2024' and says, 'Thematic has 32 employees (October 2024, LinkedIn).'
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 AWS Sample Feb 7, 2024 Nearmap Founded in 2008, Nearmap uses aerial camera technology and in-house vision and ML pipelines to help organizations track changes, such as urban growth, the effects of natural disasters, and changes in tree coverage. "Using our extensive data on AWS, I demonstrated that Adelaide, Australia, for example, lost 9.8 percent of its… Amazon S3 · Amazon SageMaker AWS Sample Sep 18, 2023 CyberGRX The legacy ML modeling solution for CyberGRX took 8 days to complete predictive modeling for all the companies in its database — 150,000 at the time. Four engineers were required to monitor and manage it, which added… CyberGRX reduced the runtime of its solution from 8 days to 1 hour for its quarterly modeling, improved staff… AWS Lambda · AWS Step Functions · AWS Step Functions Distributed Map 