Repository navigation
Name AI agents up front in the README intro - #13
Merged
Merged
Conversation
The opening said "people and systems" and only named AI agents in the audience paragraph, and never said the demos are driven by talking to an agent. Borrow the intro page's "Why build it?" paragraph and its definition of GAP so the README and the site describe the problem and the protocol the same way, and say how you try the demos. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"Was this approved?" collided with the draft's approval decision, and "why does it say this?" read as a request for the author's reasoning. Ask the two questions a receiver can actually get answered, in the same words on the README and the intro page. Drop the status line's note about talking to an agent and say it once, plainly, in the demo section. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A review thread is where "who signed off on it?" usually lives; an agent session is where "what was this based on?" often ends. List both, on the README and the intro page, so the places match the questions and the tools, people, and AI agents named before them. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The intro doesn't need the formal term yet. Call the records a context packet that travels with each release, as "Why GAP?" does, and leave "release proof" to "How GAP works," where it is defined. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"Think of them as…" told the reader what to do instead of saying what happens. Say that records of the rules, sources, and decisions travel with each released version as a context packet. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"As a context packet" read like a term the reader had to learn. Make it a plain comparison; the guides introduce the term later. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"Check which version was released" read clinically. Say that a receiver can read the content and check who signed off on it and what it was based on, answering the questions the opening paragraph asks. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"Without recreating the original workflow" read clinically. Name the review thread and agent session from the opening paragraph instead. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The README's opening paragraph described the problem as content passing between "people and systems." AI agents first appeared in the third paragraph. The documentation site already puts agents in the problem statement, so the two had drifted apart.
Shared with the intro page. The README's first paragraph and the "Why build it?" paragraph in
documentation/docs/intro/index.mdxnow say the same thing, word for word. Both ask the two questions a receiver usually can't answer, "what was this based on?" and "who signed off on it?" They say the answers stay behind "in a review thread, an agent session, or someone's memory," and note that an AI agent receiving content may have different context from the one in which it was created. The new questions replace "was this approved?", which collided with the draft's approval decision (approval doesn't release anything), and "why does it say this?", which could read as asking for the author's reasoning, something GAP doesn't record.Definition. The README's second paragraph opens with the intro page's definition of GAP. It used to continue with "A release proof connects…" and three terms not yet defined. It now says that records of the rules, sources, and decisions travel with each released version, "like a packet of context," echoing the context packet in "Why GAP?", and says that a person or an AI agent receiving it can read the content and check who signed off on it and what it was based on, answering the opening paragraph's two questions. "Release proof" and profiles are still introduced in "How GAP works."
Demos. The "Explore applications" section adds one sentence: each walkthrough is a conversation with an AI agent connected to the demo server.
Because the README and the intro page now share a paragraph, an edit to one should go to the other.
pnpm docs:buildpasses.🤖 Generated with Claude Code