What I'm building next, and what I'm still weighing. No dates. No promises. The biggest item from the last round is out: 0.8.0 puts your own edits through the same review as everyone else's, with a Propose mode, drafts, and a Linked panel for the documents around the one you're in. Stet is early, and this list moves when testers talk. The fastest way to push something up is to say so in the Discord.
Now
In progress. This is what the next releases are made of.
0.8.0 lets you write on a draft and apply it yourself. Next is sending that draft to a collaborator as a proposal they review, so the propose and review loop works between people, not just between you and an agent.
The Linked panel already shows a link to a missing document as "not found". The next step is treating that as a review signal: an edit that adds a link to nowhere gets flagged before it lands.
Stet could keep count of how you actually review, and adjust to it. Fifty trivial approvals in a row is a good argument for it to stop asking.
A push or a fetch that fails should say so. Today too much of it happens quietly in the background, and quiet is the wrong default for the part of the app that moves your work between machines.
When an agent rewrites a whole document, the review pane should stay fast and legible instead of trying to draw every word of it.
Up for discussion
Six big directions. None committed, none ordered. This is exactly what founding members get to shape: tell me which one you'd use tomorrow, and which you never would.
A rename or a changed decision in one document usually means edits in four others. Stet could show that blast radius up front, help make the follow-on edits, and record the originating change and its consequences as one reviewable unit. Links landed first, in 0.8.0, because waves need them.
Google Docs and Sheets already link to a Stet file, in and out, but the feature is immature. Make that bridge solid first, then add the other places teams keep their documents: Notion, Confluence.
Today the browser view reads, comments, and approves. Writing in it is the obvious next ask, and the hard part is doing it without quietly turning Stet into a cloud editor with a local backup.
Today you bring your own agent and it edits files on disk. Two ways to go further: embed an AI chat in Stet itself, signed in or with your own API key. Or run it the other way and connect a hosted workspace to a tool directly, so a chat assistant proposes a change through Stet and the attribution comes with it. Review stays exactly as strict either way.
HTML is the markdown of slides, one-pagers, and visual content, and agents already write it. Stet would review it the same way it reviews prose: every edit a proposal, rendered so you review the slide, not the tags.
The stack makes it feasible. Demand decides when. If Windows is the one thing stopping you, this is the easiest vote to cast.
Better support for charts, image embedding, and the other advanced markdown features writers reach for.
Everything here came from testers or from watching people use Stet. If something you need is missing, or in the wrong bucket, tell me. Email works, and so does the feedback button in the app.