Workflow · saas · workflow

Grammarly builds an on-device personal language model for iOS keyboard personalization

Mobile phone keyboards fail to recognize personal vocabulary such as nicknames or project-specific terms, giving unhelpful auto-corrections that disrupt the user experience.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User types unfamiliar term
The workflow begins when a user types a word not recognized by the standard dictionary.
Tools used
Grammarly Keyboardregex filtersmemory-mapped key-value store
Outcome

The personalized language model was shipped to over 5 million mobile devices and produced a significant decrease in reverted suggestions and a slight increase in accepted suggestions, indicating better modeling of how users communicate.

Results
Volumeover 5 million
Source

https://www.grammarly.com/blog/engineering/personal-language-model/

How we source this →

Grounding & classification
Source type: technical build writeup
15 fields verified against source quotes.
personalizationmetric backednamed customerproduction runtime claimedtools describedworkflow describedsoftwareaccuracy improvementtechnical build writeup