Data and identity
From a messy OFLC name to an employer_id
We normalise the name and compare it with legal names and a maintained alias list, using the state when the agent passes it. A name is assigned only at a confidence of 0.80 or higher; anything less comes back as candidates. No language model runs when your agent asks. The alias and group lists are reviewed with the help of AI models, and a name is added only with documented evidence.
Kept apart, on purpose
- Amazon.com Services≠AWS≠Amazon.com Inc.
- Waymo LLC≠Google LLC
- Deloitte Consulting≠Deloitte Tax≠Deloitte & Touche
Source
The public file, values as published
Certified LCA and PERM cases from the disclosure files of the Office of Foreign Labor Certification, October 2019 through 2026-06-30. Case numbers, FEINs, job titles and worksites come back as DOL published them; what we compute, such as an employer_id or a group, shows its reason and confidence.
3,466,142 certified LCA cases and 727,091 certified PERM cases were decided through Jun 2026, from 24 disclosure files. Coverage →
identify_employer(query="google", state="CA") # → emp_us_google_llc · 0.96 · alias+state identify_employer(query="Delta") # → assigned: false · ambiguous · 5 candidates