AWS Only

Anthropic Models UsedSaaSGen AI

Firemind Accelerates ePilot’s Email Management with AI-Driven Summaries

ePilot, a SaaS provider, needed an efficient way to manage and summarise lengthy email threads within their CRM. Firemind developed a GenAI-powered tool that generates actionable email summaries and suggested replies, streamlining ePilot's email management process and reducing manual workload.

AWS ONLY ·

Firemind Accelerates ePilot’s Email Management with AI-Driven Summaries

ePilot, a SaaS provider, needed an efficient way to manage and summarise lengthy email threads within their CRM. Firemind developed a GenAI-powered tool that generates actionable email summaries and suggested replies, streamlining ePilot's email management process and reducing manual workload.

At a glance


ePilot is a leading SaaS platform that empowers businesses to streamline complex product and service offerings, particularly in the renewable energy and energy efficiency sectors. By providing a comprehensive CRM system, ePilot simplifies intricate processes and transforms them into seamless digital experiences for both consumer and corporate clients.

Challenge

ePilot faced difficulties in managing and responding to long email threads, which were time-consuming and prone to errors.

Solution

Firemind implemented an AI-driven solution that generates email summaries, next steps, and suggested replies using a Retrieval-Augmented Generation (RAG) model.

Services Used

Amazon OpenSearch Serverless
Amazon Bedrock
AWS Lambda
Amazon S3

Outcomes

Email responses generated within 10 to 30 seconds.
Significant reduction in manual effort for processing email threads.

Business challenges

Enhancing email management for better efficiency

As ePilot continued to grow and support an increasing number of businesses in the renewable energy sector, they recognised the need to continually enhance their CRM platform to meet evolving client demands. The growing complexity and volume of communications, particularly lengthy and detailed email threads, presented a new challenge. As their clients’ communication needs expanded, managing these email threads efficiently became more difficult, potentially impacting response times and customer satisfaction.

To stay ahead of these challenges and continue providing exceptional service, ePilot sought a solution that could streamline the management of email communications. They aimed to implement a system that could quickly and accurately summarise long email threads, pinpoint key discussion points, and generate precise responses. By reducing the manual effort required for these tasks, ePilot’s goal was to allow their users to focus on higher-value activities, all while ensuring that their communications remained accurate and responsive to customer needs.

"Firemind's PULSE tool was able to quickly and accurately summarise vast datasets of customer surveys, ensuring we could take action against any negative customer experience elements."

Dean Macfadyen, Data Platform Engineer — Generative AI Customer

Solution

AI-powered email summarisation and response generation

To tackle ePilot’s challenge, Firemind developed an AI-powered solution centered around a Retrieval-Augmented Generation (RAG) model. The process began with ePilot providing a set of email threads, which Firemind used to create a custom knowledge base. This knowledge base was built using Amazon Bedrock and Amazon OpenSearch Serverless, where the email threads were indexed and embedded into a vector database, allowing for efficient retrieval of context-specific information.

The solution involved several key steps:

Data Preparation & Indexing: The raw email threads provided by ePilot were first cleaned and converted into a format suitable for indexing. These were then stored in Amazon S3 and indexed using an embeddings model, specifically Titan Embeddings G1, to ensure the retrieval of relevant chunks of information from the knowledge base.

Email Summarisation: For each email thread, the latest message was extracted, and an AI model (Claude) was used to generate a topical summary. This summary served as a query to the knowledge base, retrieving up to 30 relevant chunks of text that were semantically aligned with the query.

Response Generation: The relevant information retrieved from the knowledge base, along with the summarised email content, was fed into the AI model to generate a comprehensive response. This included a summary of the entire email thread, suggested next steps, and a reply email draft that aligned with the tone and context of the conversation.

The entire process was designed to be quick, with the AI generating a response within 10 to 30 seconds. This marked a significant improvement over the manual process, which could take anywhere from 5 to 30 minutes or more. The solution was integrated seamlessly into ePilot’s CRM platform, enabling users to manage email communications more efficiently and accurately.

Quick response time:

The AI solution generates email responses within 10 to 30 seconds, vastly improving response times compared to the previous manual process.

Reduced Manual Effort:

By automating the summarisation and response generation, ePilot’s CRM users experience a significant reduction in manual workload.

Optimised resource management

AWS CloudFormation simplified infrastructure provisioning and maintenance, improving overall system efficiency.

Why Firemind

Firemind’s track record of delivering custom AI-driven solutions that seamlessly integrate into existing systems ensured ePilot could enhance their email management process without disrupting their operations.

1920%

Workflow speed increase

1,000 documents in 12.5 minutes compared to 4 hours by human operator

88%

Keyword accuracy

for leading categories within data modelling & training

Added value

We were also able to take all stakeholders on a journey concerning how Cloud Adoption and Machine Learning would benefit their customers and their business continuity, all in a 12 week timeline from start to finish.

Get in touch

Want to learn more?

Seen a specific case study or insight and want to learn more? Or thinking about your next project? Drop us a message below!