doc: create ai-guidelines and include to CONTRIBUTING by RafaelGSS · Pull Request #62105 · nodejs/node

RafaelGSS · 2026-03-04T21:24:24Z

As discussed in today's TSC meeting.

cc: @nodejs/tsc @BridgeAR

Co-Authored-By: Beth Griggs <bethanyngriggs@gmail.com>

nodejs-github-bot · 2026-03-04T21:24:30Z

Review requested:

@nodejs/tsc

doc/contributing/ai-guidelines.md

joyeecheung · 2026-03-05T11:56:14Z

There may be some ideas we can borrow from https://llvm.org/docs/AIToolPolicy.html - for example "good first issue" should not be picked up by AI is a good one.

doc/contributing/ai-guidelines.md

Co-authored-by: Aditi <62544124+Aditi-1400@users.noreply.github.com> Co-authored-by: Joyee Cheung <joyeec9h3@gmail.com>

RafaelGSS · 2026-03-05T14:04:23Z

There may be some ideas we can borrow from https://llvm.org/docs/AIToolPolicy.html - for example "good first issue" should not be picked up by AI is a good one.

I took inspiration from https://github.com/zulip/zulip/blob/main/CONTRIBUTING.md#ai-use-policy-and-guidelines

Renegade334 · 2026-03-05T09:31:27Z

doc/contributing/ai-guidelines.md

+* **Do not post AI-generated messages** in pull requests, issues, or the
+  project's communication channels.


What is the intended action to take when this occurs? This currently comprises a significant proportion of GH traffic on the core repo; if we are making this a guideline, I would anticipate it applying to a lot of issues/PRs.

If that recurring, we should ping the author to stop that, if that doesn't work, we escalate it to TSC/Moderation.

I would recommend allowing pull requests descriptions and commit messages. It's quite useful for those. I would limit this to "when responding to humans".

I generally disagree with pull requests descriptions. I find them too verbose and stating the obvious.

nit

Suggested change

* **Do not post AI-generated messages** in pull requests, issues, or the

project's communication channels.

* **Do not post AI-generated messages** in pull requests, issues, or the

project's communication channels. Including a quote from a chat-bot, or using

such tool to rephrase (or translate) your message does not count as an

"AI-generated message".

EDIT: hum I guess that's already covered by the last item. What I find weird is that we start by saying "Don't send AI-generated messages", while we're still accepting AI-generated content 🤔

What about something like:

Suggested change

* **Do not post AI-generated messages** in pull requests, issues, or the

project's communication channels.

* **Do not post messages generated entirely by AI** in pull requests, issues, or the

project's communication channels.

So it emphasizes it is fully AI generated, extremely verbose descriptions that suck.

doc/contributing/ai-guidelines.md

mcollina · 2026-03-05T15:57:00Z

doc/contributing/ai-guidelines.md

+
+* **Edit generated comments critically.** LLM-produced comments are often
+  verbose or inaccurate. Remove comments that simply restate what the code
+  does; add comments only where the logic is non-obvious.


I would add a "do not disappear" section. Fly-by PRs are problematic. It's ok to close PRs if one cannot pursue them further, while stalling block progress.

mcollina · 2026-03-05T15:58:27Z

doc/contributing/ai-guidelines.md

+* **Do not post AI-generated messages** in pull requests, issues, or the
+  project's communication channels.


I would recommend allowing pull requests descriptions and commit messages. It's quite useful for those. I would limit this to "when responding to humans".

mcollina · 2026-03-05T15:59:17Z

doc/contributing/ai-guidelines.md

+* **Verify accuracy** of any LLM-generated content before including it in a
+  PR description or comment.
+* **Complete pull request templates fully** rather than replacing them with
+  LLM-generated summaries.


Do we have a template? I thought those are for issues, not PRs.

Not strictly a template: https://github.com/nodejs/node/blob/main/.github/PULL_REQUEST_TEMPLATE.md?plain=1

tniessen · 2026-03-06T09:44:51Z

doc/contributing/ai-guidelines.md

+  [commit message guidelines][].
+
+* **Test thoroughly.** AI-generated code must pass the full test suite and
+  any manually written tests relevant to the change. Existing Tests should not


Suggested change

any manually written tests relevant to the change. Existing Tests should not

any manually written tests relevant to the change. Existing tests should not

aduh95 · 2026-03-09T09:07:46Z

CONTRIBUTING.md

+
+Node.js expects contributors to understand and take full responsibility for
+every change they propose. Pull requests consisting of AI-generated code the
+contributor has not personally understood, tested, and verified will be closed


nit

Suggested change

contributor has not personally understood, tested, and verified will be closed

contributor has not personally understood, tested, and verified shall be closed

Changing it from "will" to "shall" makes it mandatory.
"will" is however fine in everyday language as a statement of intention.

What I'm trying to convey is that we cannot guarantee that such PR will definitely be closed, but it's the intention. I guess we could use might instead:

Suggested change

contributor has not personally understood, tested, and verified will be closed

contributor has not personally understood, tested, and verified might be closed

I understand your intentions and I've made an alternative suggestion in #62105 (comment) which should indicate that the likely outcome is for the PR to be closed, without actually guaranteeing this action.

MikeMcC399 · 2026-03-09T13:37:52Z

doc/contributing/ai-guidelines.md

+
+Pull requests that consist of AI-generated code the contributor has not
+personally understood, tested, and verified waste collaborator time and
+will be closed without review.


Suggested change

will be closed without review.

will be subject to closure without additional review.

MikeMcC399 · 2026-03-09T13:40:25Z

CONTRIBUTING.md

+contributor has not personally understood, tested, and verified will be closed
+without review.


Suggested change

contributor has not personally understood, tested, and verified will be closed

without review.

contributor has not personally understood, tested, and verified will be subject to closure

without additional review.

MikeMcC399

Added some minor text suggestions about PR closure

doc: create ai-guidelines and include to CONTRIBUTING

8fa167d

Co-Authored-By: Beth Griggs <bethanyngriggs@gmail.com>

nodejs-github-bot added the doc Issues and PRs related to the documentations. label Mar 4, 2026

UlisesGascon approved these changes Mar 5, 2026

View reviewed changes

joyeecheung reviewed Mar 5, 2026

View reviewed changes

doc/contributing/ai-guidelines.md Outdated Show resolved Hide resolved

Aditi-1400 reviewed Mar 5, 2026

View reviewed changes

doc/contributing/ai-guidelines.md Outdated Show resolved Hide resolved

Apply suggestions from code review

cee1884

Co-authored-by: Aditi <62544124+Aditi-1400@users.noreply.github.com> Co-authored-by: Joyee Cheung <joyeec9h3@gmail.com>

Renegade334 reviewed Mar 5, 2026

View reviewed changes

mcollina requested changes Mar 5, 2026

View reviewed changes

lpinca approved these changes Mar 5, 2026

View reviewed changes

Aditi-1400 approved these changes Mar 6, 2026

View reviewed changes

tniessen reviewed Mar 6, 2026

View reviewed changes

aduh95 reviewed Mar 9, 2026

View reviewed changes

MikeMcC399 reviewed Mar 9, 2026

View reviewed changes

		* Do not post AI-generated messages in pull requests, issues, or the
		project's communication channels.

	any manually written tests relevant to the change. Existing Tests should not
	any manually written tests relevant to the change. Existing tests should not

	contributor has not personally understood, tested, and verified will be closed
	contributor has not personally understood, tested, and verified shall be closed

	will be closed without review.
	will be subject to closure without additional review.

		contributor has not personally understood, tested, and verified will be closed
		without review.

Uh oh!

Conversation

RafaelGSS commented Mar 4, 2026

Uh oh!

nodejs-github-bot commented Mar 4, 2026

Uh oh!

Uh oh!

joyeecheung commented Mar 5, 2026

Uh oh!

Uh oh!

RafaelGSS commented Mar 5, 2026

Uh oh!

Choose a reason for hiding this comment

Uh oh!

RafaelGSS Mar 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

aduh95 Mar 9, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

MikeMcC399 Mar 9, 2026 • edited by aduh95 Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

MikeMcC399 left a comment

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

14 participants

RafaelGSS Mar 5, 2026 •

edited

Loading

aduh95 Mar 9, 2026 •

edited

Loading

MikeMcC399 Mar 9, 2026 •

edited by aduh95

Loading