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

doc/contributing/ai-guidelines.md

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

It's not possible to fulfil the instructions "Complete pull request templates fully" based on the contents of https://github.com/nodejs/node/blob/main/.github/PULL_REQUEST_TEMPLATE.md?plain=1 so it looks like this sentence needs to be removed.

doc/contributing/ai-guidelines.md

CONTRIBUTING.md

doc/contributing/ai-guidelines.md

CONTRIBUTING.md

Co-authored-by: Tobias Nießen <tniessen@tnie.de> Co-authored-by: Antoine du Hamel <duhamelantoine1995@gmail.com> Co-authored-by: Mike McCready <66998419+MikeMcC399@users.noreply.github.com> Co-authored-by: Efe <dogukankrskl@gmail.com>

gurgunday

lgtm

indutny

I'd be against this contribution policy update. While many different opinions exist on the licensing terms of the code produced by LLMs, my opinion is that the generated code isn't explicitly licensed and attributed to the original authors so it cannot be considered open source regardless of the used prompt.

mcollina · 2026-03-17T17:44:59Z

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.


Suggested change

* **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.

* **Verify accuracy** of any LLM-generated content before including it in a

PR description or comment.

joyeecheung · 2026-03-17T17:50:33Z

In #61478 (comment) , regarding the usage of Claude Code, @mcollina suggested:

As it seems that you have a different position on this issue, I will bring this to the attention of the @nodejs/tsc for an official vote. On a side note, I would also officially summon the topic at the next OpenJS board meeting.

I added it to the TSC agenda tomorrow for awareness/context collection before moving to a proper vote. @indutny sorry about the short notice since this is just one day ahead of the meeting, but if you'd like to join the meeting to present your points please let us know.

mcollina

lgtm with a sentence removed

indutny · 2026-03-17T18:04:35Z

@joyeecheung thanks for considering me for this! I'd be happy to join if the time isn't in conflict with my work meetings tomorrow. Could you send me an invite, please?

mcollina · 2026-03-17T18:08:29Z

nodejs/TSC#1830 this is the issue. It might be reschedueld to the next meeting if there is low attedance given the timezone.

I think we can schedule the discussion for April 1st which will be in the morning PT so a lot of people can join, and I would table the vote for that session. I would try to get an answer from the Board by then.

jasnell · 2026-03-17T18:16:38Z

Let's make sure it's on the agenda for a time more convenient for the majority of TSC members. That said, I can say right now that I'm -1 on blocking this on those grounds.

joyeecheung · 2026-03-17T18:19:50Z

I've updated the agenda tomorrow to mark it FYI (as in, it doesn't need to be discussed this week, but worth taking a look and do some homework before discussions happen). In any case, decisions won't be made in meetings, and this likely needs a proper vote.

jasnell · 2026-03-17T18:26:48Z

doc/contributing/ai-guidelines.md

+* **Own every line you submit.** You are responsible for all code in your
+  pull request, regardless of how it was generated. Be prepared to explain
+  any change in detail during review.


Suggested change

* **Own every line you submit.** You are responsible for all code in your

pull request, regardless of how it was generated. Be prepared to explain

any change in detail during review.

* **Own every line you submit.** You are responsible for all code in your

pull request, regardless of how it was generated. This includes ensuring

that AI-generated or AI-assisted contributions satisfy the project's

[Developer's Certificate of Origin][] and licensing requirements. Be

prepared to explain any change in detail during review.

(would need a DCO link added at the bottom of the page also)

3n-mb · 2026-03-18T19:49:52Z

[from vote on AI and in context of quoted there PR]

If someone uses an advanced tool, like LLM, should everyone have a higher baseline for expectations?

Take a look at initial review in github.com/#61478 , looks like begging to use node's style for ... core node.
Picture an analogous PR into Linux kernel, and Linus' reaction. Seriously.

This tool, LLM, is supposed to do things in style. Instead there was a re-implementation of path.normalize() ?
Where would a hacker look for SQL-inline style place for an attack?

User of an advanced tool has responsibility to provide more advanced result. Of course, in coding, LoC count is not a metric for being better.

For my 25 years, usage of more advanced tooling brought better results.
May be, user of LLM must do work of avivkeller who did 39 (or so) comments in review. Was he the first human to look into that code?
And when user of LLM does due diligence on code, results may be very good.

Should LLM's code be considered a starting point, not a ready PR?

May I note, as user of node.js, an unhealthy dynamic regarding this, and a need to frame constructive approach, also as an example for whole industry.

nodejs/TSC#1831 (comment) is opened with, quote: "In order to surpass the blocks of ..." as if we are here to score social points, using heavy words. Please, snap out of it.

We need to re-frame topic in nuances that matter to code. Otherwise, we either get more hack-able artifacts, or, throw away baby with the bath water. And you all here seem to have enough emotional shrapnel to swing either way. Please don't. For the sake of us, your users.

jasnell · 2026-03-19T00:18:12Z

doc/contributing/ai-guidelines.md

+
+## Core principle
+
+Node.js expects contributors to understand and take full responsibility for


Suggested change

Node.js expects contributors to understand and take full responsibility for

Node.js requires contributors to understand and take full responsibility for

sorry for resolve, hit the wrong button in UI.

If required, what's the consequence for failing this requirement? We've implemented so many policies without consequence and had to correct that later, we shouldn't do that here.

If this is merged (I'm unconvinced it should be), we have to define consequences.

It seems like the obvious consequence is that the contribution will not be accepted.

jasnell · 2026-03-19T00:18:27Z

doc/contributing/ai-guidelines.md

+## Core principle
+
+Node.js expects contributors to understand and take full responsibility for
+every change they propose. The answer to "Why is X an improvement?" should


Suggested change

every change they propose. The answer to "Why is X an improvement?" should

every change they propose. The answer to "Why is X an improvement?" can

jasnell · 2026-03-19T00:19:19Z

doc/contributing/ai-guidelines.md

+AI tools may assist contributors, but must not replace contributor judgment.
+When using AI as a coding assistant:


Suggested change

AI tools may assist contributors, but must not replace contributor judgment.

When using AI as a coding assistant:

Contributors may use AI tools to assist with contributions, but such tools

never replace contributor judgement.

When using AI as a coding assistant:

jasnell · 2026-03-19T00:21:10Z

doc/contributing/ai-guidelines.md

+Node.js values concise, precise communication that respects collaborator time.
+
+* **Do not post messages generated entirely by AI** in pull requests, issues, or the
+  project's communication channels.


I'm less convinced this one is necessary. It's also difficult to enforce. These should follow the same rules as contributions... whatever is posted, you're responsible for, so use appropriate discretion.

It's only difficult to enforce if it's low quality prose, though, in which case this item seems like it'd be needed.

I think this also disenfranchises people that use an AI to help them write English, as it might not be their first language

avivkeller · 2026-03-19T00:47:42Z

CONTRIBUTING.md

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


Suggested change

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

without review.

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

without review.

avivkeller · 2026-03-19T00:48:48Z

doc/contributing/ai-guidelines.md

+
+## Using AI for code contributions
+
+AI tools may assist contributors, but must not replace contributor judgment.


Suggested change

AI tools may assist contributors, but must not replace contributor judgment.

AI tools may assist contributors, but must not replace human judgment.

avivkeller · 2026-03-19T00:49:29Z

doc/contributing/ai-guidelines.md

+* **Understand the codebase first.** Do not skip familiarizing yourself with
+  the relevant subsystem. LLMs frequently produce inaccurate descriptions of
+  Node.js internals — always verify against the actual source. When using an AI
+  tool, ask it to cite the exact source files/PRs/docs it’s relying on, and then


Suggested change

tool, ask it to cite the exact source files/PRs/docs it’s relying on, and then

tool, ask it to cite the exact source it’s relying on, and then

avivkeller · 2026-03-19T00:50:58Z

doc/contributing/ai-guidelines.md

+
+## Using AI for communication
+
+Node.js values concise, precise communication that respects collaborator time.


Suggested change

Node.js values concise, precise communication that respects collaborator time.

Node.js values concise, precise communication that respects collaborator and contributor time.

avivkeller · 2026-03-19T00:51:42Z

doc/contributing/ai-guidelines.md

+* **Link to primary sources** — code, documentation, specifications — rather
+  than quoting LLM answers.


Suggested change

* **Link to primary sources** — code, documentation, specifications — rather

than quoting LLM answers.

* **Link to primary sources** — code, documentation, specifications — rather

than quoting LLM answers or linking to LLM chats.

italojs · 2026-03-19T19:34:24Z

doc/contributing/ai-guidelines.md

+  feedback and iterate until the work lands or is explicitly closed. If you
+  can no longer pursue it, close the PR. Stalled PRs block progress.
+
+* **Edit generated comments critically.** LLM-produced comments are often


I would recommend adding an extra rule to not push "linter" changes that LLM usually does, it's pretty frequent at meteor, and dirty the commits and PR history

mcollina · 2026-03-20T09:38:34Z

Given this is receiving a lot of attention, I had AI prepare a summary of all discussions within the Linux Kernel: https://gist.github.com/mcollina/8a4f2ee2e64d38edb90760016e89f919.

I don't see anything more critical than the Linux Kernel, and it's also the flagship project of our parent Foundation. Given that this proposal follows that concept and is currently blocked on a similar basis, I think documenting our position on what has already been debated elsewhere is relevant.

On a more practical note, Chrome/Chromium (which V8 is part of) allows AI assistance. As a result, we are likely already including code developed with the assistance of AI in our tree.

mcollina · 2026-03-22T21:24:17Z

@indutny can you please send a PR to add youself back to active contributors and use the “request chages” button in both PRs? Thanks.

domenic · 2026-03-25T01:57:30Z

Hi all,

I wanted to weigh in as a community member and former Node.js core contributor in favor of these proposed guidelines. And, in particular, to say that it's important that Node.js not try to instate a blanket ban on AI-assisted contributions, as I've seen some calls for.

A lot of large open-source projects, including ones I've worked on like Chromium, V8, jsdom, and Undici, are seeing huge benefit from AI. This is clearest when the AI is wielded by core contributors working in their element, and any policy which prevented core contributors from taking advantage of AI uplift would hurt the project a lot.

But it's also important for a project that wants to stay relevant and welcome outside contributors. I know of at least one large open source project, Servo, which has lost long-time community contributors due to their anti-AI stance. When a modern, AI-using developer wants to contribute to a nascent browser engine, and they have a choice between Servo (AI-unfriendly) and Ladybird (AI-welcoming), they choose Ladybird. If Node.js were to ban AI assistance, I think it would find itself in a similar situation with regard to other competing runtimes.

I fully acknowledge that AI-generated contributions have created new problems and there needs to be some reckoning with it. I like the Rust community survey's common ground section for summarizing these issues. The guidelines proposed here seem like a good framework to start with, but surely evolution will occur over time. Regardless, I'm heartened to see this PR as a starting point, for establishing clearly that while AI assistance needs to be treated with care, it's also very much a part of modern software development.

Thanks!
-Domenic

delan · 2026-03-25T06:00:36Z

I know of at least one large open source project, Servo, which has lost long-time community contributors due to their anti-AI stance.

which long-time community contributors were those? as far as i’m aware, even the most vocally AI-positive contributors in Servo have continued doing great work on the project.

bmuenzenmeyer · 2026-03-27T01:05:58Z

CONTRIBUTING.md


+## [AI Use Policy and Guidelines](./doc/contributing/ai-guidelines.md)
+
+Node.js expects contributors to understand and take full responsibility for


this first sentence seems intentionally to be the same as the full policy document, which now has a suggested change. marking this here to resolve whether or not the language should continue syncing, if it should change

Ethan-Arrowood · 2026-03-27T15:50:58Z

doc/contributing/ai-guidelines.md

+  be removed or modified without human verification. Do not rely on the LLM
+  to assess correctness.
+
+* **Do not disappear.** If you open a PR, follow it through. Respond to


What is / can we link to our official policy on "stale" or stalled PRs? Like regardless if its involving AI do we have a policy to close out PRs after a certain amount of time? If not, should we?

Right now our automation closes PRs if they are both older than a year and have had no activity in the past sixth months, but IMO we should make that just six months (no year clause)

mcollina · 2026-03-27T18:11:56Z

@RafaelGSS Can you please add a link to https://openjsf.cdn.prismic.io/openjsf/aca4d5GXnQHGZDiZ_OpenJS_AI_Coding_Assistants_Policy.pdf (official AI policy)?

This document already aligns for the most part, which should mention the Assisted-by: git commit tag (like the kernel).

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

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

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

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

aduh95 reviewed Mar 9, 2026

View reviewed changes

CONTRIBUTING.md Outdated Show resolved Hide resolved

MikeMcC399 reviewed Mar 9, 2026

View reviewed changes

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

MikeMcC399 reviewed Mar 9, 2026

View reviewed changes

CONTRIBUTING.md Outdated Show resolved Hide resolved

This comment was marked as resolved.

Sign in to view

RafaelGSS and others added 2 commits March 13, 2026 10:55

Apply suggestions from code review

483c41b

Co-authored-by: Tobias Nießen <tniessen@tnie.de> Co-authored-by: Antoine du Hamel <duhamelantoine1995@gmail.com> Co-authored-by: Mike McCready <66998419+MikeMcC399@users.noreply.github.com> Co-authored-by: Efe <dogukankrskl@gmail.com>

fixup! Apply suggestions from code review

8944958

RafaelGSS requested a review from mcollina March 13, 2026 16:39

RafaelGSS added the commit-queue-squash Add this label to instruct the Commit Queue to squash all the PR commits into the first one. label Mar 13, 2026

gurgunday approved these changes Mar 13, 2026

View reviewed changes

RafaelGSS added the author ready PRs that have at least one approval, no pending requests for changes, and a CI started. label Mar 14, 2026

joyeecheung mentioned this pull request Mar 17, 2026

Virtual File System for Node.js #61478

Open

indutny suggested changes Mar 17, 2026

View reviewed changes

joyeecheung added the tsc-agenda Issues and PRs to discuss during the meetings of the TSC. label Mar 17, 2026

joyeecheung mentioned this pull request Mar 17, 2026

Node.js Technical Steering Committee (TSC) Meeting 2026-03-18 nodejs/TSC#1830

Open

mcollina reviewed Mar 17, 2026

View reviewed changes

mcollina approved these changes Mar 17, 2026

View reviewed changes

mcollina mentioned this pull request Mar 17, 2026

Vote on AI contributions nodejs/TSC#1831

Open

jasnell reviewed Mar 17, 2026

View reviewed changes

jasnell reviewed Mar 19, 2026

View reviewed changes

openjs-meetings-bot bot mentioned this pull request Mar 19, 2026

Node.js Technical Steering Committee (TSC) Meeting 2026-03-25 nodejs/TSC#1840

Open

avivkeller reviewed Mar 19, 2026

View reviewed changes

italojs reviewed Mar 19, 2026

View reviewed changes

MoLow approved these changes Mar 25, 2026

View reviewed changes

openjs-meetings-bot bot mentioned this pull request Mar 26, 2026

Node.js Technical Steering Committee (TSC) Meeting 2026-04-01 nodejs/TSC#1845

Open

bengl mentioned this pull request Mar 26, 2026

doc: add policy on LLM-generated contributions #62447

Open

bmuenzenmeyer reviewed Mar 27, 2026

View reviewed changes

Ethan-Arrowood reviewed Mar 27, 2026

View reviewed changes


		## Core principle

		Node.js expects contributors to understand and take full responsibility for

	Node.js expects contributors to understand and take full responsibility for
	Node.js requires contributors to understand and take full responsibility for

	every change they propose. The answer to "Why is X an improvement?" should
	every change they propose. The answer to "Why is X an improvement?" can

		AI tools may assist contributors, but must not replace contributor judgment.
		When using AI as a coding assistant:

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


		## Using AI for code contributions

		AI tools may assist contributors, but must not replace contributor judgment.

	tool, ask it to cite the exact source files/PRs/docs it’s relying on, and then
	tool, ask it to cite the exact source it’s relying on, and then


		## Using AI for communication

		Node.js values concise, precise communication that respects collaborator time.

		* Link to primary sources — code, documentation, specifications — rather
		than quoting LLM answers.


		## [AI Use Policy and Guidelines](./doc/contributing/ai-guidelines.md)

		Node.js expects contributors to understand and take full responsibility for

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!

Uh oh!

Uh oh!

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!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

This comment was marked as resolved.

Uh oh!

gurgunday left a comment

Choose a reason for hiding this comment

Uh oh!

indutny left a comment • 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!

joyeecheung commented Mar 17, 2026

Uh oh!

mcollina left a comment

Choose a reason for hiding this comment

Uh oh!

indutny commented Mar 17, 2026

Uh oh!

mcollina commented Mar 17, 2026

Uh oh!

jasnell commented Mar 17, 2026

Uh oh!

joyeecheung commented Mar 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

3n-mb commented Mar 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

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!

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!

indutny left a comment •

edited

Loading

joyeecheung commented Mar 17, 2026 •

edited

Loading

3n-mb commented Mar 18, 2026 •

edited

Loading

mcollina commented Mar 20, 2026 •

edited

Loading