Nordstrom is one of America’s leading fashion retailers, serving customers across hundreds of stores and online at nordstrom.com. Founded in 1901 and headquartered in Seattle, Nordstrom runs data-intensive operations at scale — from real-time inventory management to personalized recommendations — with BigQuery at the center of its analytics infrastructure.

After migrating to BigQuery, Nordstrom’s engineering and FinOps teams faced a challenge familiar to any organization running complex workloads at scale on a completely different platform: spend was rising, but the visibility to understand what was driving it, and the tools to act on it effectively, weren’t keeping pace.

"Rabbit's slot optimizer alone has reduced our BigQuery spend by 47% since we turned it on. That's not a projection or a modeled estimate, that's real spend that never hit our bill. For a single feature of a platform to move the needle that significantly is something I wouldn't have believed before seeing it ourselves."

Bryce Ageno Principal Software Engineer, Nordstrom

The Challenge: Diminishing Returns on Manual Optimization

Nordstrom’s engineering team had been tackling BigQuery costs the conventional way: manual SQL tuning, query audits, and custom-built cost dashboards. But as the platform scaled, these approaches hit a ceiling. “Before Rabbit, manual SQL tuning was delivering diminishing returns and consuming significant engineering time” says Pete Bruno, FinOps Lead & Platform TPM, Nordstrom.

Two problems were compounding simultaneously. First, slot waste (the gap between what BigQuery’s native autoscaler provisioned and what queries actually consumed) was running at 57.3%. With Nordstrom’s query volumes, that waste translated into substantial recurring overspend. BigQuery’s autoscaler bills for a minimum of 60 seconds for any provisioned slots, meaning short-lived spikes triggered by burst workloads were being billed in full even when the slots went largely unused. This “Autoscaler Tax” accumulated silently across every reservation, every day.

Second was the time engineers spent trying to diagnose it. Without granular visibility into which projects and queries were driving costs, the team had no reliable way to prioritize where optimization effort would land hardest. Manual audits were slow, partial, and a constant drain on engineering capacity that could have been used building product.

The Solution: A Platform Built Around How BigQuery Actually Bills You

Nordstrom brought Rabbit in to close that gap. What distinguished Rabbit from other tools wasn’t just the reporting layer — it was the depth of understanding baked into the platform’s design and translated into automated savings.

"Rabbit doesn't just optimize how you use BigQuery, they rethink how BigQuery billing itself can be worked in your favor. The slot optimizer, automated pricing routing per job, and storage billing model recommendations are all examples of capabilities built around a deep understanding of how BigQuery charges you. That kind of creative product thinking is rare. It's the difference between a cost reporting tool and a platform that actually changes your bill."

Bryce Ageno Principal Software Engineer, Nordstrom

Rabbit addressed Nordstrom’s cost problem across multiple dimensions:

• Slot optimization: Rabbit’s automated Max Slot Optimizer dynamically adjusts each reservation’s maximum slot configuration in real time (every few seconds) preventing the Autoscaler Tax from compounding. Critical pipelines retain the capacity they need; idle and low-activity periods are handled cost-efficiently. Slot waste fell from 57.3% to 18.6%, a 38.7% relative improvement in reservation efficiency.

• Dynamic pricing optimizer: Rabbit’s Job Optimizer automatically routes each query to the cheapest available pricing model (on-demand or capacity-based) at the job level, in real time, without SQL changes or pipeline refactoring needed. Alongside slot optimization, this became a significant contributor to Nordstrom’s recurring savings, with an additional 10% in forecasted savings projected from continued rollout.

• Storage billing model recommendations: Rabbit analyzed access patterns across Nordstrom’s datasets and recommended the optimal storage billing model (logical or physical) per dataset. On analytics infrastructure at Nordstrom’s scale, these recommendations unlock savings that are otherwise easy to miss in aggregate billing views.

• Project- and query-level cost visibility: Rabbit maps cost attribution at the project and query level, giving Nordstrom’s FinOps and engineering teams the granularity they needed to stop guessing and start acting. Engineers could see exactly which workloads were driving spend, and prioritize accordingly.

"Rabbit's deep visibility into BigQuery quickly identifies project and query-level drivers of inefficient spend, significantly increasing the ROI of our optimization efforts."

Pete Bruno FinOps Lead & Platform TPM, Nordstrom

Results: Sustainable Savings and Engineering Time Recovered

“Rabbit’s slot optimizer bent our cost curve immediately with minimal effort.” says Pete Bruno, FinOps Lead & Platform TPM, Nordstrom. The slot optimizer alone reduced Nordstrom’s BigQuery spend by 47%. “That’s not a projection or a modeled estimate,” said Ageno, “that’s real spend that never hit our bill.” Monthly savings have continued to grow as additional automations have been activated and reservation configurations refined. Cumulatively, Rabbit’s BigQuery automation has delivered over $1M+ in total savings, with monthly savings continuing to climb.

Reservation efficiency improved by 38.7% — a structural gain that compounds over time. Engineers who had been spending significant time on manual SQL tuning and cost diagnostics reclaimed an estimated 400 hours per month, capacity that now goes toward building rather than chasing bills.

For Nordstrom’s FinOps and platform engineering teams, Rabbit didn’t just reduce a line item. It changed how BigQuery spend is managed, shifting the team from reactive auditing to proactive, automated cost governance.

"The Rabbit team operates like a partner, not a vendor. When we brought up Looker Core costs climbing as a pain point, they leaned into that conversation with us rather than redirecting us back to their feature list. That willingness to engage openly on problems outside their current scope is what separates them from every other tool in this space."

Bryce Ageno Principal Software Engineer, Nordstrom