Logistics ops · Production

Flexport modernizes global freight search with Algolia, achieving 9 ms average search time at 4M searches per month

The problem

Flexport needed to make shipment tracking data accessible and actionable for end users in an industry that had not changed its processes in over 100 years, while supporting products with hundreds of unique attributes that all needed to be searchable at global scale.

Workflow diagram · grounded in source
1
Shipment lookup triggered
trigger
“users are able to identify and locate their merchandise in transit using any identifier the customer may have”
2
Multi-index search query
integration
“Multi-Index Search: Search into multiple indices with a single query”
3
Results delivered in milliseconds
output
“turn what used to take several minutes to locate into milliseconds”
Reported outcome

Algolia became mission-critical infrastructure for Flexport, reducing shipment lookup time from several minutes to milliseconds and enabling standardized data collection for both internal support teams and clients.

Reported metrics
Index size3M
Searches per month4M
Average search time9 ms
Shipment lookup timeseveral minutes to locate into milliseconds
Reported stack
AlgoliaQuery Categorization
Source
https://www.algolia.com/customers/flexport
Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

Algolia became mission-critical infrastructure for Flexport, reducing shipment lookup time from several minutes to milliseconds and enabling standardized data collection for both internal support teams and clients.

What tools did this team use?

Algolia, Query Categorization.

What results were reported?

Index size: 3M; Searches per month: 4M; Average search time: 9 ms; Shipment lookup time: several minutes to locate into milliseconds (source-reported, not independently verified).

How is this logistics ops AI workflow structured?

Shipment lookup triggered → Multi-index search query → Results delivered in milliseconds.