10x
“10x annotation speed improvement on tracking data”
As published on encord.com, April 2026. Captured by usedby on Oct 7, 2026.
What happened
Hudl's Applied Machine Learning team uses Encord as the central annotation and data management layer in its MLOps pipeline, annotating sports video and sensor data for model training. Hudl's own models pre-label the data, a validation agent flags errors, and annotators and data scientists work together in one workflow.
Summary written by usedby from the source page, in English. The figures are those of Encord and Hudl, not ours.
- 40%“With the validation agent in place, the same process is now 40% faster.”
By integrating Hudl's own pre-labelling pipeline into Encord, use cases that previously required approximately 10 hours of manual annotation now take around 1 hour.
Encord has broken down barriers between annotation and data science. Pre-labelling has probably been the biggest game changer for us. We've seen a 10x speed improvement on some of our most demanding projects.
What the story claims, and what we checked
We compared the story with its live page on Oct 7, 2026.
- The figure: 10xCheckedPrinted word for word on the page, near the name of Hudl.
- The passage quoted aboveCheckedCopied word for word from the page, near the name of Hudl.
- The publication dateCheckedRead from the page’s own metadata, never guessed.
- Hudl uses EncordCheckedConfirmed line. Latest check across sources: Oct 7, 2026.
- The result itselfNot checkedWe quote it; we did not measure it.




