Semantic layer speeds time to market with metrics in one location

Customer-facing dashboards that load in 2 seconds

Breakthrough is a leading provider of sustainable fuel and freight solutions for shippers that reduce cost, create efficient networks, and decarbonize transportation. All their product offerings analyze vast datasets to offer optimization strategies for reducing transportation fuel spend, carbon footprint, and freight spend. With large enterprise customers, such as Unilever and Danone, relying on their products, they need to address many different types of customers. With both a SaaS application and service-based product offerings, Breakthrough’s data stack needs to allow for both self-serve capabilities and tools for professional analysts.

The Need for Speed

A few years ago, the Breakthrough team built the analytics for one of their products on top of very custom SQL hitting a Postgres database “that would crawl with these analytical queries,” said Juan Muñoz, Chief Technologist at Breakthrough. Muñoz knew they needed to re-platform the solution to get the performance they required, so they tested out Cube in a proof-of-concept, “We figured out: Yes, we can do this now. This will solve all our issues.” Once the solution was tested, the real work began, and the team rewrote the product with Cube as the semantic layer and both Preset and their own visualization framework on the front-end.

The Semantic Layer Architecture Revolutionizes The New Stack

Today, clients send data on their truckload movements, which Breakthrough then enriches. This part of the data pipeline, called Load Processing Pipeline, is written in Data Flow in Google Cloud Platform (GCP). Then the data gets dumped into Google BigQuery where dbt picks it up and does more auditing. Finally, data is sent through Cube, the semantic layer, to the front-end framework that Breakthrough developed in React with their own visualization toolkit including sliders, date pickers, and other useful widgets all mapped to Cube queries. For their service-based product offerings, the data is visualized in Preset where the Breakthrough team has more capabilities to do additional analysis.

To help serve all the different client needs, Breakthrough provides many different data experiences. For those who want to dig into the analytics, they have dashboards that allow for slicing and dicing the data in many ways. For others that just want answers, they have built machine learning that will recommend actions and optimizations based on the analysis. Breakthrough's consulting-focused services are the primary user of Preset dashboards for their personalized analysis for their clients that can go even deeper into analyzing the data.

The Semantic Layer Underneath is A Single Place to Create Metrics

All the different data experiences are supported by Cube - the semantic layer underneath it all. “In just one place, we can define and share metrics across both our SaaS app and our service-based products. The metric only has to be implemented once. That’s a huge value to us.”

“We no longer have to embed all the calculations everywhere and have gotten rid of the tedious copying and pasting of all the code and formulas. Now it’s all in one place. And that has allowed us to grow.”

That growth and scale comes in many different forms. With their new data stack and Cube in the center, they can now add new visuals “super fast.” Before Cube, the team would have to change the database query, the resolver, the UI, and effectively the whole stack to add new data or visuals.

“We had one request that was scheduled for a month of work. Once we implemented Cube we did it in just a few days. That speed of turnaround happens because we’ve separated out a shareable data asset that can be recombobulated with our visual assets. That was a huge performance win for us in terms of development. The time to release new features and visuals decreased significantly - from months to just days.”

With this new data stack with Cube as the semantic layer, query performance has greatly improved. Breakthrough is able to get more people onto the platform with a much faster experience. “It’s super speedy. We’ve seen a great improvement in load time.”

Looking to the future - The meaning of a semantic layer

“The new Cube architecture allows us to build a sliceable cube of data, put Cube on top of it, and eliminate rework. It’s a huge architectural win for us.”

Now that they’ve seen success with their products, the team plans to extend Cube to all of their other core products in addition to pushing out more features, charts, graphs, and other ways to experience data. They’ll be doing more machine learning to analyze pricing and other optimizations - all analytics backed by Cube - as well as extending more capabilities across all their product lines.

“Having that semantic layer that can serve not just a BI tool, not just an application, but both - so I can have the team model our business in one spot and have it available in multiple places has allowed us to grow and scale our products much faster than ever before.”