scripod.com

We Made a Document Editor Where Humans and AI Work Side by Side

AI & I

Mar 11
AI & I

AI & I

Mar 11

Shownote

Every has unveiled a new product, built by CEO Dan Shipper. It's called Proof, a free, open-source, live collaborative document editor built for humans and AI agents to work in together.  Proof started as a Mac app designed to show the provenance of AI-w...

Highlights

This episode explores Proof—a new open-source, real-time collaborative editor built explicitly for human-AI co-authorship—not as a replacement for writers, but as a shared workspace where humans and AI agents collaborate as peers.
00:00
Proof and agents speed up creative writing and make it better
05:08
The killer feature of Proof is live, collaborative editing where humans and AI agents interact in real time
07:29
The app serves as a natural glue for team collaboration, fitting the agent-native philosophy
09:07
An agent-native product can be so without having an agent in it
16:20
Agent Experience (AX) is as critical as UX and requires feedback loops
20:52
Proof creates a shared space for agents and humans to collaborate, making agent contributions visible and editable in context
24:31
Current attempts at agent-driven landing page updates suffer from duplication and document pollution
26:53
Codex wrote a Proof doc about adding a dashboard to Proof, showcasing human-agent collaboration
32:47
Agents summarize and structure writing differently than humans, enabling creative workflows
40:03
One speaker asks if Proof will be an open-source product
42:19
Proof serves as a good example for builders, especially those needing a text editor for their apps

Chapters

Collaborative AI Writing Tools
00:00
Introduction and the origin story of Proof
02:00
From Mac app to collaborative web editor
07:24
What makes Proof “agent native”
09:00
Live demo: watching an agent join and write inside a shared document
14:30
How Austin uses Proof for creative writing and food journalism
20:51
The challenge of multiple agents editing one document simultaneously
24:30
When AI-written docs are better read by agents than by humans
26:48
Brandon’s agent-to-agent collaboration loop
29:30
Proof as a lightweight scratchpad vs. existing tools like Notion and GitHub
37:09
Why Proof is open source and what that means for builders
42:18

Transcript

Dan Shipper: It became clear that what we needed was a live, collaborative, web-based document that humans and agents could be in at the same time, making changes and leaving comments and doing track changes and all that kind of stuff. Austin Tedesco: I'm...