Turn scattered material into work you can put your name on
What to do once it is collected, how to ask questions that land, how the Agent picks up the pen — our own practice, plus the trade-offs behind the product.
Take it straight into your next deck
Overview graphic, demo clips, brand mark — all downloadable originals, so you never have to screenshot the product yourself.
Web capture demo
Paste a link → parsed and filed, about 15 seconds.
Extension demo
Save a whole chat thread in one click.

Local deployment
A real capture of the openclaw local setup, ready for technical decks.
Brand mark
Square icon, PNG, works on light and dark.
From material to finished work
Pick a topic, or read straight through. Every post maps to a feature that actually ships.
Why we did not build a nicer chat box
The chat box is the default shape of every AI product, and also its ceiling: context is used once and thrown away. Notes on the trade-off we made.
Read postFrom material to a deck you will actually use
Generating slides is easy. Wanting to use them afterwards is hard. Most of our effort went into the second half: editable, exportable, structurally sound.
Read postConnected in five minutes: extension and skill
Two paths in: the extension handles capture, the skill handles use. Which one you need depends on where you are stuck.
Read postLet the Agent read and write your material
The ceiling of a chat window is that you keep re-feeding it context. With the skill installed, the Agent reads your library directly and writes back to your notes.
Read postAsk with citations: every claim, traceable
Drop a PDF in and ask where the risk sits. Whether the answer is usable depends on whether it says "risk is on page 7, paragraph 3".
Read postCollecting is not the finish line
Chats, links, files, images — different sources, different shapes, one question when you need them: where was that conclusion? Here is how we file them.
Read post