Hapag-Lloyd stands as one of the world’s leading liner shipping companies, operating a modern fleet of 313 container ships with a total transport capacity of 2.5 million TEU (Twenty-foot Equivalent Unit—a standard unit of measurement for cargo capacity in container shipping). The company maintains a container capacity of 3.7 million TEU, which includes one of the industry’s largest and most modern fleets of reefer containers. With approximately 14,000 employees in the Liner Shipping Segment and more than 400 offices spread across 140 countries, Hapag-Lloyd maintains a robust global presence. Through 133 liner services worldwide, we facilitate reliable connections between more than 600 ports across the continents.

The company’s Digital Customer Experience and Engineering team, distributed between Hamburg and Gdańsk, drives digital innovation by developing and maintaining customer-facing web and mobile products.

Over the past years, the Digital Customer Experience and Engineering team has evolved from a delivery-focused channel into a true digital product driver, with strong customer focus, engineering excellence, and measurable business impact. We take end-to-end ownership of our digital products, combining customer-centric innovation with engineering craft to directly support growth and business outcomes. Building on a modern, independently owned tech stack and a high level of engineering maturity, we are committed to staying at the forefront of technology. Now, we are taking the next step by moving toward becoming AI-native, investing heavily in artificial intelligence as a core capability. This journey is about amplifying powerful engineering with AI to build smarter products, faster innovation, and greater customer value.

So far, our customer feedback analysis process had largely been manual and reactive. Especially ahead of review ceremonies, manually analyzing customer feedback could take hours, sometimes days, when hundreds of ratings and comments needed to be reviewed. Every two weeks, Product Managers exported customer feedback data as CSV files, read through large volumes of comments, and manually categorized sentiment and themes. Although this work was valuable and deeply connected to product decisions, it was also repetitive, time-consuming, and difficult to scale, limiting flexibility whenever faster or deeper insights were needed.

With our generative AI solution, we fundamentally changed this approach. Instead of manually aggregating and interpreting feedback, we now automate the entire workflow: collecting customer comments, extracting sentiment, identifying themes, and surfacing actionable insights. Product Managers and teams can focus less on operational analysis and more on strategy, innovation, and creating exceptional user experiences.

In this post, we walk you through our generative AI–powered feedback analysis solution built using Amazon Bedrock, Elasticsearch, and open-source frameworks like LangChain and LangGraph. Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models from leading AI companies such as AI21 Labs, Anthropic, Cohere, DeepSeek, Luma, Meta, Mistral AI and Amazon through a single API, along with a broad set of capabilities you need to build generative AI applications with security, privacy, and responsible AI. With this solution, you can automatically ingest customer comments, generate rich summaries, and deliver targeted insights. This allows our product teams to make faster, smarter decisions and drive continuous improvement.