The Contract
The Reader is useful. The way we ship it is a deliberate stance. We watched authors get burned by tools that trained on their work, by editors that turned out to be personas, by black-box assistants that nobody could audit. We do not do those things. Here is the exact mechanics, surface by surface.
I.
There is no “generate next paragraph” button. No auto-complete. No ghost text. The Reader reads your manuscript and reports back; what ends up on the page is what you typed. If you want a chatbot to draft for you, that’s what ChatGPT is for, and that is the line we will not cross. The book is yours.
II.
DraftProse calls your chosen provider with training opt-out enabled. We do not run our own models. We do not retain your prose for any analytic purpose. We do not sell it. There is no internal team reading manuscripts to improve features.
III.
The Reader runs against the provider you pick — Anthropic, OpenAI, Google Gemini, or a local endpoint (Ollama, LM Studio, anything OpenAI-compatible). On the Studio tier you bring your own key; calls bill to your own account and your prose never enters our infrastructure beyond passing through.
Keys are encrypted at rest with AES-256-GCM, the same primitive your bank uses for card storage. You can clear any key from settings at any time.
IV.
Each Reader surface — pacing read, plot read, character voice workshop — has an inspect button. Click it to see exactly what was sent to the provider and exactly what came back. No black box. If you want to know what we asked, you can know.
V.
The character voice workshop only voices fictional characters you have created in your own manuscript, grounded only in scenes you wrote. We do not market “AI editors” designed to feel like real human professionals. We do not train personas on real authors’ published work. That is a line we will not cross.
VI.
Your prose is stored in a SQLite database tied to your account on Argonode infrastructure. You can export every document as Markdown anytime from your project menu. Delete your account and we wipe everything irrevocably. No tombstone, no archived copy, no soft-delete.
VII.
A typical Reader call is a few thousand tokens of output — roughly comparable to streaming a few seconds of video. Bigger calls (plot overview on a full novel) are correspondingly more. We disk-cache identical reads, so the second time you ask the same thing it costs zero new compute. We do not think this makes the Reader “green.” We do think a cached read is far less than the same prompt re-run in five chat tabs every morning, and we want you to make that call yourself.
VIII.
Each Reader call carries the minimum context required to do its job. The inspect button on every surface shows you the exact text. The high-level breakdown:
Pacing read
Scene titles + word counts + dialogue ratios. No prose content sent.
Plot read
First ~600 characters of each scene (excerpts). The rest of your prose is not sent.
Character voice workshop
The character profile fields you filled in, plus up to 6 scenes (~800 chars each) where the character’s name appears. Your message to the character is sent verbatim.
IX.
We treat this page as the contract. If you spot a gap, an ambiguity, or something we could explain better, email hello@argonode.studio.