One object model. Every view is a projection of it.

The workbench is built around the Rejection Graph — a single structure linking each rejection to the claims, elements, cited art, specification support, and response options it touches. Parse it once; read it from any angle; trace any line back to the record.

The Rejection Graph

The source of truth, not a report

Cards, tables, charts, and drafts are all renderings of the same graph. Edit a node — re-segment a claim, correct a misread reference label, accept or reject a mapping — and everything downstream re-derives. There is no second copy of the truth to drift out of sync.

  • Navigable top to bottom: rejection → affected claims → element → examiner-cited passage → analysis → response → supporting spec passage → draft language.
  • Every generated node carries a source link and a confidence indicator as fields — not as cosmetic afterthoughts.
  • Re-running the analysis replaces the graph cleanly; selected strategies and accepted edits are part of the matter's living record.
application
└─ office action
└─ claim → elements
└─ rejection · §103
├─ cited art → verified passage
├─ response options → amendments
└─ estoppel risk
Statutory analysis

Each basis has its own path.

Rejections branch on statutory ground. The workbench runs the right analysis for each and presents findings, never conclusions.

§101

Eligibility

Detects the rejection, summarizes the examiner's eligibility theory, and classifies the asserted judicial exception. Surfaces claim features that may tie to a practical application or technical improvement — as a framework for your argument, never an eligibility verdict.

Alice/Mayopractical application
§102 / §103

Novelty & obviousness

Separates primary from secondary references, summarizes the motivation-to-combine rationale and flags it when conclusory, and looks for teaching-away and non-analogous-art angles. Identifies dependent-claim limitations that may carry the day.

KSR / Grahamteaching away
§112

Definiteness & support

Flags §112(a) written-description and enablement concerns, §112(b) antecedent-basis and indefiniteness issues, and §112(f) functional terms that may need corresponding structure in the specification.

antecedent basis§112(f)
§103 Claim 1 · element 2 arguably disclosed
Examiner's characterization
“Smith discloses a sensor generating environmental readings (¶[0012]).”
What the reference actually says — Smith, US 2018/0123456
“…includes a temperature sensor 102 configured to generate temperature readings at regular intervals.”
Smith [0012] verified
Examiner's words next to the reference's words — the heart of traversal
Element mapping & provenance

What the examiner said, next to what the reference says

Each limitation is classified against the cited art — expressly disclosed, arguably disclosed, inferred by the examiner, missing or weak, or unclear — with an explanation and a quoted passage.

Then the quote is checked against the source text. Found verbatim, it's anchored to an exact offset. Paraphrased, it's marked partial. Absent, it's marked unverified and held out of the coverage analysis — so a confident-sounding sentence can't stand in for evidence that isn't there.

  • Verified — quote located in the reference, anchored to its paragraph, figure, or claim.
  • Partial — substance present but not verbatim; flagged, not trusted.
  • Unverified — not found in the source; surfaced as caution, never counted as disclosure.
Amendment builder

Narrow the claim. See exactly what it costs.

Generate and edit amendment candidates with tracked changes against the current language — each one checked against the original disclosure before you rely on it.

support

Specification support

Maps each amendment to where the original spec, claims, or drawings support it — and flags when the document that would supply support was never provided.

new matter

New-matter & antecedent basis

Flags language that may introduce new matter under §132, plus antecedent-basis breaks and inconsistent terminology the amendment would create.

scope

Scope cost & estoppel

Surfaces how much claim scope a narrowing amendment surrenders and the prosecution-history estoppel it risks — so allowance is never bought blindly.

Strategy board

Options, weighed — not an answer, handed down

Per rejection, response paths are laid out as a comparison: argument strength, scope cost, support strength, estoppel risk, and drafting burden. Argument-only traversals are kept distinct from amendment-based paths. You select a path and add notes; the unselected options stay visible for comparison and flow nowhere you didn't choose.

Response draft & Word export

A skeleton you finish — exported to file

The draft is organized by rejection, built only from the strategies you selected, with sources carried per section and low-confidence passages marked. Export to .docx with USPTO strikethrough/underline amendment markup, highlighted [ATTORNEY: …] placeholders, and a page-broken “Attorney Work Product — remove before filing” appendix of open issues and sources. The system never files.

A living record

Everything is overridable. Nothing is forgotten.

correction loop

Correct the parser, re-run the analysis

Every field the parser produced is editable. Fix a misread reference label and examiner-shorthand matching improves; re-segment a claim and its stale mappings drop and rebuild. Corrections are marked, so you can see what was changed.

history

An append-only matter timeline

Every action — a parse, an edit, an accepted suggestion, a generated draft — is recorded to the matter's history. The record enriches as you work it, and your judgment, once entered, governs.

U.S. non-final & final Office actions

Built narrow, built serious.
§101 · §102 · §103 · §112.

A small, rigorous Office-action workflow for attorneys who want leverage without losing control.