Working on documents with your AI chat
Revise is a new word processor designed for the post-AI age, aiming to improve the inefficient process of working with documents and AI chat apps. The goal is to create a seamless and collaborative editing experience between humans and AI agents. Revise supports tracked changes, margin comments, and real-time conversations, making it a powerful tool for document creation and editing.
- ▪Revise is a word processor that allows collaborative editing between humans and AI agents.
- ▪The platform supports tracked changes, margin comments, and real-time conversations.
- ▪Revise has first-class MCP support, making it compatible with various AI apps and systems.
Hacker News (AI / LLM) files mainly under ai. We currently carry 4,338 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Revise |
| Canonical URL | https://revise.io/blog/08-10-2026/working-on-documents-with-your-ai-chat |
| Publication time | Mon, 10 Aug 2026 19:46:44 +0000 |
| Retrieval time | 2026-08-10T19:55:47.952Z |
| Last seen | 2026-08-10T19:55:47.952Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | 8PjV_yK3TQNz · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Paul Graham said 20 years ago, “Look at something people are trying to do, and figure out how to do it in a way that doesn't suck.” We are doing this for documents in the AI age. Pasting or uploading a document into ChatGPT.com, forcing it to rewrite the entire thing, and copying or downloading the output... objectively sucks. It’s inefficient and disjointed.Agentic, collaborative editingThe goal with Revise is to build a new word processor for the post-AI age. Things are going pretty well—our web app has a growing user base and the Revise Agent has become very reliable.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Revise.
Discussion
0 commentsMore from Revise
