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
Hapag-Lloyd enhances corporate audit efficiency with GenAI on Databricks
…ories / Hapag-Lloyd CUSTOMER STORY Ensuring corporate audits are smooth sailing Hapag-Lloyd uses Databricks to enhance audit efficiency with GenAI 66% Decrease in time spent creating new written findings from bullet points (5…
Description
German shipping company Hapag-Lloyd fine-tuned Databricks' open-source DBRX model and built a RAG chatbot to automate audit finding generation and executive summaries, cutting review time per finding by 66% and executive summary review time by 77%.
…mmaries. Daniel’s team dubbed this prototype the Finding Generation Interface. Hapag-Lloyd engineers then fine-tuned Databricks’ open source DBRX model on 12T tokens of carefully curated data. The solution architecture included a series of steps, starting with data ingest…
…only 5 minutes creating a new finding from bullet points, down from 15 minutes. This represents a 66% decrease in review time per finding — a huge time savings given that there are, on average, seven findings per audi…
…a huge time savings given that there are, on average, seven findings per audit. The time required to review each executive summary has decreased by 77%, from 30 minutes to just 7 minutes. Building the Finding Generation Interface and chatbot through Databricks not on…
Company
Hapag-Lloyd
…rporate audit department. Manual audit processes impede efficiency and accuracy Hapag-Lloyd is a leading global liner shipping company with a rich history and a commitment to providing efficient, reliable and sustainable transportation services. With a vast network spanning over 400 offices in 140 countries, Hapag-Lloyd ope…
Industry
Transportation
…rporate audit department. Manual audit processes impede efficiency and accuracy Hapag-Lloyd is a leading global liner shipping company with a rich history and a commitment to providing efficient, reliable and sustainable transportation services. With a vast network spanning over 400 offices in 140 countries, Hapag-Lloyd ope…
Problem
Hapag-Lloyd's corporate audit process involved several manual instances of documentation and report writing that were time-consuming and led to inconsistencies, and its existing infrastructure, including an AWS SysOps account, did not support rapid setup and deployment of the AI models needed for audit optimization.
…port writing,” explained Ulrich Daniel, Director of Corporate Audit Analytics. “As this process involved several manual instances, the key was to get the quality on a very high level.” The primary use cases for leveraging generative AI included enhancing the effi…
…eps, leading to inefficiencies and potential inconsistencies in documentation. “Our existing infrastructure, including tools like vector databases, did not support the rapid setup and deployment of AI models required for our audit optimization efforts. Ensuring the accessibility of instances was also a challenge. We had an AWS Sys…
Solution
Hapag-Lloyd fine-tuned Databricks' open-source DBRX model on 12 trillion tokens of curated data to build a Finding Generation Interface that generates audit findings and summaries, used Databricks MLflow to automate the evaluation of prompts and models across the ML lifecycle, and built a chatbot using Gradio integrated with Databricks Model Serving that uses retrieval-augmented generation (RAG) to let auditors query documents in natural language.
…mmaries. Daniel’s team dubbed this prototype the Finding Generation Interface. Hapag-Lloyd engineers then fine-tuned Databricks’ open source DBRX model on 12T tokens of carefully curated data. The solution architecture included a series of steps, starting with data ingest…
…izing results and storing them in a Delta table for easy access and retrieval. Using Databricks MLflow, Hapag-Lloyd was able to automate the evaluation of prompts and models. This reduced the time-consuming manual process of generating and reviewing audi…
…pport through the full lifecycle,” added Daniel. To further enhance efficiency, a chatbot interface was developed using Gradio and integrated with Databricks Model Serving. This chatbot allowed auditors to query specific information from documents usi…
Business value
Auditors now spend only 5 minutes creating a new finding from bullet points, down from 15 minutes, a 66% decrease in review time per finding, and the time required to review each executive summary decreased 77%, from 30 minutes to just 7 minutes.
…ng a scalable and high-quality framework for audit and documentation processes. Auditors now spend only 5 minutes creating a new finding from bullet points, down from 15 minutes. This represents a 66% decrease in review time per finding — a huge time savings given that there are, on average, seven findings per audi…
…a huge time savings given that there are, on average, seven findings per audit. The time required to review each executive summary has decreased by 77%, from 30 minutes to just 7 minutes. Building the Finding Generation Interface and chatbot through Databricks not on…
AI capabilities
Generative AI, Large Language Models, Retrieval-Augmented Generation
The chatbot used retrieval augmented generation (RAG) to provide accurate and contextually relevant responses, further improving the audit process.
Technology
Agent Bricks, MLflow
…Details Industry : Manufacturing Use Case : Artificial Intelligence Cloud : AWS Product : Agent Bricks Ready to get started? Try Databricks for free Learn more about our product Talk…
…izing results and storing them in a Delta table for easy access and retrieval. Using Databricks MLflow, Hapag-Lloyd was able to automate the evaluation of prompts and models. This reduced the time-consuming manual process of generating and reviewing audi…
Deployment model
cloud
…e this post Details Industry : Manufacturing Use Case : Artificial Intelligence Cloud : AWS Product : Agent Bricks Ready to get started? Try Databricks for free Learn more…
Deployment options
cloud
…e this post Details Industry : Manufacturing Use Case : Artificial Intelligence Cloud : AWS Product : Agent Bricks Ready to get started? Try Databricks for free Learn more…
Headline outcome
…ooth sailing Hapag-Lloyd uses Databricks to enhance audit efficiency with GenAI 66% Decrease in time spent creating new written findings from bullet points (5 minutes vs. 15 minutes) 77% Decrease in review time per executive summary (7 minutes vs. 30 minutes) Ha…
Use case type
Content generation
…returns far better results than the previously tried models,” explained Daniel. This model, a transformer-based decoder-only LLM, was pretrained on extensive datasets, making it suitable for generating high-quality audit findings and summaries. Daniel’s team dubbed this prototype the Finding Generation Interface. Hapag-L…
