About · AI use
Where AI is used, and where it is not
This archive is built with substantial AI assistance. This page says exactly where, which models, and what to do when you find a mistake.
Step by step
| Step | Model involved? | What happens |
|---|---|---|
| Acquisition | No | Documents are located and retrieved by script and by hand from courts, agencies, RECAP, and Congress.gov. Every retrieval is logged with its source URL and date. |
| Preservation and hashing | No | The file is stored as retrieved and its SHA-256 recorded. |
| OCR | No | Scanned documents go through Tesseract. No language model touches the text. |
| Text extraction | No | Text is pulled from the document's own text layer or from the OCR output. Extraction is not generation: nothing is added, rewritten, or "cleaned" by a model. |
| Titles | Partly | Raw filing names are normalized by script. A model proposes a title where the script cannot; a human-maintained override table supplies the final title, and each override is checked against the document, its docket entry, or its first-page heading. |
| Cross-references | Partly | Models propose links between documents. The "More filings in this case" lists on filing pages are built from the record facts, not by a model. |
| Descriptions | Partly | The one-line lede on a filing page and the one-line description on a source-document page are assembled from the record's own fields. Where a document page carries a summary, a Claude model drafted it from the document's text on that page, a script checked every date, number, name and docket cite in the draft against that text, and a sample of every batch was read by a person before it appeared; the summary is labeled on the page. A summary is a navigation aid, never a source: cite the document. |
| Verification passes | Partly | Models help run the checks (link targets, sourcing, page structure). Scripted gates decide whether a page ships; a model's opinion does not. |
| Numbers | No | Figures come from the underlying data files and the documents, never from a model's memory. Every count on the program guides was measured on the archive's own files when the page was built. |
| Guides | Partly | The program guides are drafted with model assistance from the archive's records and checked line by line against the pages they link to before they publish. |
The documents themselves are never AI-generated.
Which models
Anthropic's Claude models have done most of the model work: the Claude 4 generation for most of the build, and later Claude models from mid-2026. No model publishes anything on its own: a draft goes through the same structural check and the same document-by-document verification before it appears on the site.
If you find an error
Go to the corrections page. Send the page URL, the passage, and the document that shows it is wrong. If the error is in extracted text, the page will be re-processed. If it is in a guide or a data table, the page is fixed.