We Made a Document Editor Where Humans and AI Work Side by Side (45 min)
ai-collaborations-with-creators ai-driven-innovation-economy ai-human-identity ai-in-everyday-life ai-in-workforce-disruption cultural-creativity-with-ai
- Release date: 2026-03-11
- Listen on Spotify: Open episode
- Episode description:
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-written text—purple for AI, green for human. But when Shipper rebuilt it as a web app with real-time collaboration, something clicked. Suddenly, everyone at Every was using it for everything from planning docs, to creative writing and even daily to-do lists. The team realized they needed a lightweight space where their OpenClaw agents and humans could co-author documents and leave comments. In this special episode, Shipper is joined by Every chief operating officer Brandon Gell, Cora general manager Kieran Klaassen, and head of growth Austin Tedesco to demo Proof live and share how it's changed the way they work. Brandon walks through a loop where his Codex agent writes a plan, Dan's personal Claw R2-C2 reviews it, and the humans just steer. Austin explains how he uses Proof to write a weekly food newsletter, texting ideas to his Claw on runs and watching an outline take shape. And Kieran makes the case that Proof's power is its lightness—just a link you can hand to any agent or colleague.The conversation covers what "agent native" means in practice, why AX (agent experience) matters as much as UX (user experience), what happens when 10 agents edit one document at the same time, and why some writing is now better read by an AI than a human.If you found this episode interesting, please like, subscribe, comment, and share!Want even more?Sign up for Every to unlock our ultimate guide to prompting ChatGPT here: https://every.ck.page/ultimate-guide-to-prompting-chatgpt. It's usually only for paying subscribers, but you can get it here for free.To hear more from Dan Shipper:Subscribe to Every: https://every.to/subscribeFollow him on X: https://twitter.com/danshipperGet started building today at framer.com/dan for 30% OFF a Framer Pro annual plan.Download Grammarly for free at Grammarly.comTimestamps 00:02:00 — Introduction and the origin story of Proof00:07:24 — From Mac app to collaborative web editor00:09:00 — What makes Proof “agent native”00:14:30 — Live demo: watching an agent join and write inside a shared document00:20:51 — How Austin uses Proof for creative writing and food journalism00:24:30 — The challenge of multiple agents editing one document simultaneously00:26:48 — When AI-written docs are better read by agents than by humans00:29:30 — Brandon’s agent-to-agent collaboration loop00:37:09 — Proof as a lightweight scratchpad vs. existing tools like Notion and GitHub00:42:18 — Why Proof is open source and what that means for buildersLinks to resources mentioned in the episode:Proof Editor: https://proofeditor.aiProof GitHub repo (open source): https://github.com/EveryInc/proofEvery's compound engineering plugin: https://github.com/EveryInc/compound-engineering-plugin
Summary
- 🚀 Proof Launch: Every launches Proofeditor.ai, a free open-source browser-based Markdown editor for real-time human-agent collaboration, evolving from a Mac app for provenance.
- 👥 Seamless Collab: Humans and agents (e.g., Claude) edit, comment, and track changes together via simple links, no logins needed, revolutionizing planning and iteration.
- 📈 Workflow Wins: Speeds creative writing, to-dos, strategies; distinguishes AI/human text; supports agent reviews/PRs, making text ‘cheap’ yet valuable.
- 🤖 Agent-Native Magic: Optimizes ‘AX’ for intuitive agent use; external agents outperform internals; enables multi-agent docs with human god-edits.
- ✍️ Writing Spectrum: AI for info-transfer (summarize via agents); humans for creative/vibe; tools like Proof bridge, preserving voice while accelerating work.
Insights
How does real-time collaboration between humans and AI agents transform everyday document workflows?
Time: 0:00 – 7:20
Category: AI in Everyday Life, AI Collaborations with CreatorsAnswer: Proof enables humans and agents to edit, comment, and track changes simultaneously in a web-based Markdown editor, making it ideal for planning docs, to-do lists, and creative outlines. This shifts work from static tools like Google Docs to dynamic, agent-inclusive spaces that speed up iteration and ensure accountability. Users report it strengthens output and integrates seamlessly into daily tasks like company planning or personal writing. (Start at 0:00)
Why has tracking AI vs. human provenance become secondary to seamless sharing in agent-assisted writing?
Time: 4:12 – 7:49
Category: AI in Everyday LifeAnswer: Initially built for distinguishing AI (purple) and human (green) text, Proof evolved into a collaborative tool because sharing plans with team members and their agents proved more valuable. Provenance matters less now that users read AI writing routinely, prioritizing live feedback loops over origin tracking. This reflects broader acceptance of AI-generated content in professional contexts. (Start at 4:12)
What defines an ‘agent-native’ app, and how can it thrive without embedded agents?
Time: 9:22 – 17:49
Category: AI-Driven Innovation Economy, AI in Workforce DisruptionAnswer: Agent-native means designing for external agents to interact seamlessly, like via shareable links that allow any agent (e.g., Claude) to join and edit without logins or skills. Proof exemplifies this by prioritizing ‘Agent Experience’ (AX) alongside UX, making it intuitive for agents through simple copy-paste integration. This approach leverages agents’ context awareness, outperforming internal agents lacking user history. (Start at 9:22)
How does cheap AI text production redefine the role of text editors and human input?
Time: 11:35 – 12:20
Category: AI in Workforce DisruptionAnswer: With agents generating text effortlessly, editors like Proof become ‘canonical’ hubs where humans rarely write but ‘god-mode’ edit key parts, manage versions, and approve changes. This inverts traditional writing: humans oversee, agents produce volumes, enabling experimentation with multi-agent edits and traffic-cop LLMs. It opens possibilities for provenance, versioning, and optimized agent workflows. (Start at 11:35)
When is AI-generated writing preferable to human text, and what does this mean for reading habits?
Time: 26:42 – 29:09
Category: Cultural Creativity with AI, AI & Human IdentityAnswer: AI excels at ‘information-transfer’ writing like plans or recaps, which humans skim or delegate to agents for summary, freeing brainpower for creative or vibe-based prose. Proof docs reveal this spectrum: agent recaps of code changes or strategies are skimmable, while personal essays demand human reading. This ‘Matrix-like’ knowledge upload via agents redefines consumption, valuing human strengths. (Start at 26:42)
How are agent-mediated reviews and PR submissions changing software development?
Time: 29:11 – 33:13
Category: AI-Driven Innovation Economy, AI in Workforce DisruptionAnswer: Teams use Proof for agent-written plans reviewed by other agents and humans, iterating via comments before executing code—non-coders submit PRs built this way. Examples include dashboards or bots, where agents like Codex and R2-C2 collaborate, accelerating builds in ‘vibe coding’ environments. This democratizes development, blending human oversight with agent execution. (Start at 29:11)
Why do lightweight, ephemeral tools like Proof outperform heavy apps for short-term plans?
Time: 38:34 – 40:45
Category: AI in Everyday LifeAnswer: Proof’s no-login, no-index design avoids ‘contamination’ of tools like Notion or GitHub, treating plans as fleeting ‘moments’ rather than permanent artifacts. Users pin links in Slack or agent-recall them, emphasizing communication over organization. This bare-bones seamlessness fosters idea-sharing without overhead, promoting if-important-keep-it-elsewhere philosophy. (Start at 38:34)