The Agent
The Agent is an assistant that works on the book itself. The other AI Tools each do one job to one chapter; the agent takes an instruction in your own words, looks around the manuscript to work out what you meant, and does it. It can answer questions too — "which chapters never mention the narrator's sister?" is a fair request, and nothing changes when you ask one.
It is experimental. It is good at bounded, checkable work — a rename carried through the whole book, an audit of something you suspect is inconsistent, a first pass at an index — and it is capable of being confidently wrong. Everything it changes is held for your review, so the way to use it is to ask, then read what came back.
Opening it
The Agent button sits in the strip down the right-hand side of the editor, below Project Settings. It opens a panel beside your chapter, and the button pulses while a request is running, so you can carry on writing in another chapter and come back to it. AI → Open Agent does the same thing, and the other entries on that menu open it with a conversation already started — see AI Tools.
Type into the box at the bottom and press Send — or just Enter, with Shift+Enter for a new line.
Attaching a file
You can show the agent a picture or a document. Use the paperclip beside Send, paste straight into the box, or drag a file onto the panel — all three do the same thing, and a message can carry up to five files of 25 MB each.
There are two quite different reasons to do it, and both work:
- A picture you want in the book. "Here's the cover — put it at the front of chapter three." The agent inserts it as a figure, and you review that insertion like any other change it makes.
- A picture you want it to work from. "Match this layout in the project settings", or "the chapter openers in this book — can you get close?" Nothing is added to the book; the agent looks at the image and changes settings.
Inkwell accepts images, PDFs and text documents (.md, .txt, .html, .tex, .docx,
.odt, .rtf). A PDF is shown to the agent as its first page and its text, so it works
either as a design to copy or as something to read. A document is read as text — the agent
can quote it and write from it, but there is nothing to insert.
A file is only stored in your book if the agent actually uses it. Attaching a picture and then deciding against it leaves nothing behind. Because storing one is a change to the book, it needs Read-write — in Read-only or Comment the agent can look at your picture and tell you what it would do with it, but not put it in.
Read-only, Comment, Read-write
The dropdown next to Send decides how much the agent may touch:
- Read-only — it can look at the manuscript but cannot change anything. The safe way to ask questions.
- Comment — it may leave, edit and remove comments, but not touch your text. Useful for a critique you want alongside the writing rather than in it.
- Read-write — it may edit, comment, and create chapters.
The setting applies to the next thing you ask, so you can drop to Read-only for a question and raise it again for the work.
Starting a conversation from the AI menu can raise it for you — the Copyeditor cannot work in Read-only — and Inkwell says so when it does. That lasts as long as that conversation; the setting you chose is what the next one you start yourself comes back to.
Watching it work
While it runs, the panel shows Working… and a row of small icons — one per thing the agent did: a chapter it read, a search it ran, a page it rendered to look at. Click any of them for the detail behind it. A rendered page shows up as a thumbnail of the page itself, so you can see what it saw. Stop ends the run; work already done stays for review.
Sometimes it produces something for you to read rather than an edit — a summary, an audit, a list. Those appear as a full-width entry in the log with an Open button.
Citations
The agent reaches the same sources as the Insert Citation button: the citation manager you have linked under Citations and Bibliography, a DOI or a web address, Semantic Scholar, and every source the book already cites. So "find a source for this claim and cite it", "check that every citation in chapter 4 still resolves", or "this work is cited twice under two different records — merge them" are all fair requests.
It prefers a source the book already uses over a fresh lookup, which is what keeps one work from appearing twice in the bibliography. Citations it inserts arrive as tracked edits like any other change, so you see each one before it is part of the book.
The same is true of an assistant connected from outside — see Connecting an AI assistant below.
Reviewing what it changed
Nothing the agent writes is final. Changes land as tracked edits, exactly like a collaborator's, in that collaborator's own colour — see Collaboration for how they are reviewed, and View Menu for how they are displayed.
The panel keeps its own tally: N changes awaiting review, with Accept all and Revert all, and beneath that one line per chapter it touched. Click a chapter's name to jump to the first edit in it, or accept and revert that chapter on its own. Changes to the book's settings or chapter order have nowhere in the text to point at, so the list is the only place they are offered.
Ink, and starting over
The agent spends ink, and spends it faster than anything else on the AI menu — it is doing more work, over more of the book. The composer shows how many drops you have left, and the run stops when you are out until your ink refills or you move to a plan with a larger allowance. A free plan includes no ink, so the agent needs a paid plan or your own API key saved under My Account.
New conversation clears the transcript and starts fresh; edits already made stay in the book for you to review. Flag sends the conversation to us when a run goes wrong, which is the most useful thing you can do with a bad answer while this is still experimental.
Connecting an AI assistant
If you would rather work in an assistant of your own than in this panel, you can connect one to the book directly, with the same three modes and the same tracked-edit review. Claude and ChatGPT both do this, and so does anything else that accepts a remote MCP connector.
Open AI → Connect AI Assistant to set it up. A fresh agent panel offers the same thing before you have asked it anything.
For each book, a checkbox controls whether connected assistants can reach it at all, and — once that's on — a Mode dropdown appears below it, offering Read-only, Comment, or Read-write, the same three modes as the panel. Different books can be set to different modes; an assistant that can freely edit one book might only be allowed to leave comments on another. Changes take effect immediately for every assistant you have already connected — no need to reconnect.
The Connector URL at the top of the dialog is what your assistant needs. It is the same URL for every book and every connection, and it is not a secret: it grants nothing on its own, and an assistant reaches only the books you have turned on, at the mode you set for each. Copy it with the button beside it, add it in your assistant, and approve access when Inkwell asks.
Claude.ai
Settings → Connectors → Add custom connector. Give it a name, paste the connector URL, and add it. Claude then sends you to Inkwell to approve the connection.
ChatGPT
Settings → Apps & Connectors → Create. Paste the connector URL, choose OAuth authentication if it asks how to connect, and approve access when Inkwell asks.
Other MCP clients
Anything that speaks MCP over HTTP — a coding agent, an editor, a desktop client — takes the same URL wherever it asks for a remote MCP server. Its own documentation will say where that is; Inkwell's side of the setup is the same either way, ending in the approval screen.
Revoking a connection
Connected assistants at the bottom of the dialog lists everything currently connected, with a button to revoke any of them. A connection lasts until you revoke it, or until a year after you approved it, whichever comes first. The list only shows connections that still work, so if an assistant disappears from it, approve it again the same way you set it up.
Letting an assistant start a project
A connected assistant can also create a new project for you, without you opening Inkwell to do it. Ask for one and it picks the kind — note, article, or book — and, if you have templates, one of those; you can say which if you care.
What arrives is what New Project would have given you, and no more. A note comes with one chapter, titled the way you named the project. An article or a book comes with the template's front matter — title page, copyright, and the rest — and no chapters yet, so ask for the chapters you want and the assistant will add them.
The new project appears in your projects list straight away, and it is turned on for AI access at Read-write so the assistant can go on to write in it. That is the same checkbox and the same Mode dropdown as any other book, in the dialog above, so you can turn it off, drop it to Comment, or delete the project outright.
One thing to expect: the starting content is not held for review the way the assistant's later edits are. It came from the template, not from the assistant, so there is nothing to accept — everything it writes after that arrives as tracked changes as usual.
Keep the book open when the assistant needs to see a page
An assistant can ask what the typeset book looks like — which page a chapter starts on, how long it runs, or for a picture of a page. Inkwell answers those from the same typeset preview your own window is showing, which is why the answer comes back almost immediately.
The catch is that it needs your window. If the book isn't open in Inkwell, the assistant can't measure or picture a page, and it will tell you so rather than guess. Everything else — reading, editing, commenting — works whether or not you have the book open. So if you've asked an assistant to tidy up your page breaks, leave the book open in a tab while it works.
An assistant's edits save as it makes them, so they appear in your window as it works rather than all at once when it finishes.