Docket

Property documents filed to the right unit, or held for a person.

Docket reads incoming leases, invoices and notices, and matches each one to a known unit. It files a document on its own only when two independent clues agree. A language model can suggest a unit to a reviewer; it never files a document.

Try a test document See the held-out results

Watch a test document get filed or held

What Docket readsdoc-0001-clean.pdf
Lease document
Synthetic property-management fixture.
Record: UNIT-0116
Address: 1510 Birch Street Apt 16
Building: BIRCH_06
Tenant: Paul Logan
Tend tax sit later talk couple sound little pass control land.
  1. Read the text

  2. Find candidate units

  3. Score the clues

  4. Decide

Recorded held-out results, played back here. Nothing is uploaded.

Try it live: ask for an invite code

How a document is decided

Docket looks for clues in the text that point at one of the known units. Each kind of clue carries a weight. A close spelling counts for part of its weight.

A document is filed on its own only when at least 2 different clues point at the same unit, and their weights add up to a score of about 0.586. If the clues name more than one unit outright (by unit number, full address or full tenant name), it waits for a person. A building code shared by many units does not count as naming one. One clue alone, even the unit number, is never enough, so a document cannot file itself just by naming a unit.

Every document files, waits for a person, or stops with a reason: a file that cannot be read at all (empty, encrypted, damaged or not a PDF) is rejected, and a document whose type question gets no answer from the model fails. Everything else that does not file waits on the review page, where a person sees the PDF, the clues, the rules' top pick and the model's suggestion side by side, and picks the unit or dismisses the document.

The model labels the document type and may suggest a unit. Its suggestion is shown to the reviewer and recorded in the trace; it is never used to file. If its type answer cannot be read, the document waits for a person, so the model can hold a document back but never file one.

Clue weights
ClueWeight
Unit number in the text0.30
Street address0.30
Tenant name0.25
Building code0.10
Unit number in the file name0.05

Held-out results

Measured on 180 synthetic test documents that played no part in choosing any setting: 28 filed, 112 held for a person and 40 rejected as unreadable files. "Rules only" is the same filing policy with no model at all.

DocketRules only
Automatic filings that were correct28 of 2838 of 38
Documents that should file, filed28 of 3938 of 39
Suggestions on the 112 documents held for a person
Held documentsCountModel rightRules' top pick right
Belong to a known unit; model asked. Right means naming that unit.623 of 6242 of 62
Belong to no unit; model asked. Right means naming none.2020 of 200 of 20
No candidate unit, so the model was not asked20not comparednot compared
The model's suggestion call failed10not comparednot compared

What it missed. The model's safety filter refused every very long test document: 40 of 440 answers across both test sets, against a limit of 2%. Those documents wait for a person instead of filing, so in the held-out set Docket filed fewer of the documents it should have than the rules alone. That missed 2 of the live test's 4 gates. Nothing was filed to a wrong unit. The full results and both missed gates

Terms and method
Held-out test
Two sets of generated documents. The tuning set, 180 documents, chose the filing threshold, 0.5857142. The held-out set, 180 documents, chose nothing. Every other figure on this page comes from the held-out set, except the live-test gates, which count the model's answers across both.
Model
Claude Haiku 5.5 on the Anthropic API, answers recorded once on 2026-11-13 and replayed with no model call.
Precision and recall
"Correct automatic filings" is precision; "should file, filed" is recall.
Uncertainty
The report gives a 95% Wilson interval for its overall figures, such as filing precision, recall and suggestion accuracy; the split rows in the suggestions table have none. These figures measure synthetic documents, not real mail.

Held-out report · Failure notes · Live-test gates

The review page

Held documents wait in one queue. Each shows the PDF, why it is waiting, every candidate unit with its score, the rules' top pick and the model's suggestion. A reviewer approves either, picks another candidate, or dismisses the document with a reason. Every step is in the document's trace.

It needs a reviewer token. To try it, run Docket locally with the quickstart, then open the review page.