Cursor invents names and genders in PR reviews

My company uses GitHub EMU and our user names are formatted as first letter of first name, followed by last name.

I’ve noticed that when reviewing PRs, Cursor tends to invent the first name and assume the gender to be male. For instance, if I’m reviewing a PR made by hford Cursor will assume the user is named Harry Ford and will use “he” or “him”. But hford is actually called Hannah Ford and she is a she.

Our full names are entered in GitHub so Cursor could look it up instead of making it up.

It made the same assumption many times, it seems pretty systematic. And every time I ask it why, it does not really come up with an answer.

So, is Cursor sexist by design? Is it to save a few chars (“he” is shorter than “she”)

I don’t know that I would call this a bug, but it happens on the Chat window. I will ask Cursor something like “Review this PR” or “read the comments on this PR” and if the PR was created or commented on by a woman, Cursor will assume her gender to be male and will make up a name instead of using her real name which is available in GitHub.

To reproduce, create a user in GitHub with a username like hford, and a first name Hannah and last name Ford, and then create a PR and ask Cursor “Review this PR” with a link to the PR. When referring to work made by hford, Cursor will make up a name (it tends to like ‘Harry’) and will refer to hford as ‘he’. This is on Windows 11, running Cursor 3.13.10 with model set to Auto. It is not blocking me, just a weird quirk.

Hi there!

We detected that this may be a bug report, so we’ve moved your post to the Bug Reports category.

To help us investigate and fix this faster, could you edit your original post to include the details from the template below?

Bug Report Template - Click to expand

Where does the bug appear (feature/product)?

  • Editor, Tab & Chat (autocomplete, Composer, in-editor agent)
  • Terminal & commands
  • Models, pricing & API keys (availability, Auto/Max, BYOK/Bedrock)
  • MCP & tools
  • Cloud Agents & Automations (cursor.com/agents, scheduled/event)
  • BugBot & Code Review
  • Cursor CLI
  • Cursor Mobile
  • Remote (SSH / Dev Containers / WSL)
  • Account, billing & login
  • Something else…

Describe the Bug
A clear and concise description of what the bug is.


Steps to Reproduce
How can you reproduce this bug? We have a much better chance at fixing issues if we can reproduce them!


Expected Behavior
What is meant to happen here that isn’t working correctly?


Screenshots / Screen Recordings
If applicable, attach images or videos (.jpg, .png, .gif, .mp4, .mov)


Operating System

  • Windows 10/11
  • MacOS
  • Linux

Version Information

  • For Cursor IDE: Menu → About Cursor → Copy
  • For Cursor CLI: Run agent about in your terminal
IDE:
Version: 2.xx.x
VSCode Version: 1.105.1
Commit: ......

CLI:
CLI Version 2026.01.17-d239e66

For AI issues: which model did you use?
Model name (e.g., Sonnet 4, Tab…)


For AI issues: add Request ID with privacy disabled
Request ID: f9a7046a-279b-47e5-ab48-6e8dc12daba1
For Background Agent issues, also post the ID: bc-…


Additional Information
Add any other context about the problem here.


Does this stop you from using Cursor?

  • Yes - Cursor is unusable
  • Sometimes - I can sometimes use Cursor
  • No - Cursor works, but with this issue

The more details you provide, the easier it is for us to reproduce and fix the issue. Thanks!

Hey there,
This isn’t Cursor picking a name or gender, and it’s not by design. In that “review this PR” chat flow, Cursor only has the GitHub username (hford) to work with - it doesn’t pull the full name from the profile - so the model fills in the blanks from the handle and tends to default to a masculine name/pronoun. There’s no name/gender logic behind it (and no “he is shorter” shortcut), which is why it can’t give you a real reason when you ask.

Two things that help today:

  1. Add a User Rule (Cursor Settings → Rules): “Refer to PR authors by their GitHub username only; never infer a name, gender, or pronouns from a username - use they/them if needed.”
  2. When the real name matters, ask the agent to run gh api users/<login> --jq .name (works on EMU).

Your underlying point - the names are in GitHub, so we could use them instead of guessing - is a fair one, and I’ve passed it to the team. More on rules here.