Continuation Drafter
Continuation claims, drafted on your own machine
A specification and the filed parent claims go in. Drafted continuation claims come out, with their defects already flagged, so you start from a marked-up draft instead of a blank page.
Free. Runs locally through Ollama, or through your own provider key. Nothing to activate.
What it actually does
Three things, and it is honest about which of them is solid.
Drafts
Reads the specification and the parent claims, then drafts continuation claims aimed at what the disclosure supports beyond the parent's scope.
Critiques
Flags per-claim 112(a) and 112(b) defects, each with a proposed fix. In our own testing this was the most useful thing it produced.
Scores
Rates drafting craft across support, definiteness, form and differentiation. Read the spread rather than the rank: a single AI judge cannot separate near-equal drafts, and we say so on the benchmark page.
Twenty-nine models, ten real patent families, one table
We ran the same ten parent and continuation pairs through every model we could host, and the interesting gap was not the one we expected.
| Your machine | Model | Index | Corpus drafted |
|---|---|---|---|
| A server with 512 GB of memory | glm-5.2 | 88.3 | 10 of 10 |
| A workstation with 64 GB | gemma4:31b | 79.8 | 9 of 10 |
| A desktop or laptop with 32 GB | gemma4:26b | 65.0 | 10 of 10 |
| A laptop with 16 GB | gemma4:12b | 62.9 | 9 of 10 |
The gap between memory tiers is larger than the gap between open and closed weights. A firm running the top row sits about 3.3 points behind the strongest closed-weight model measured, with nothing leaving the building. How this was measured, and what it does not tell you.
Where your specification goes
On the local path, inference runs on your hardware and the specification is not transmitted anywhere. That property belongs to the local path, not to the tool as a whole: point it at a remote provider and the specification reaches that provider, which suits published material and is a decision you make per matter for anything unpublished.
Local inference is not unique to this tool. What is unusual is the shape: a binary you download and run today, rather than a deployment behind a sales cycle and a security review.