The author
Explain the project's purpose, what you want checked and the problems you already know about. You decide what to change after reviewing the findings.
The exchange
Think your project works, or could work, but have no one to ask? Swap reviews of work made with AI: give one, get one.
Crossreview brings together people who make things with AI and people willing to check them. Ask for help, receive critique and exchange solutions. You do not need to write code: a report, lesson plan, care guide, research plan, design or tool can be reviewed, and practical knowledge from law, care, education or any other field is welcome. The aim is useful work grounded in evidence, with less sycophancy (agreement that leaves weak claims unchallenged) and more honest critique.
Bring a research protocol, an analysis, a tool, a design or another project made with AI. Say what you want checked. A review is another person's assessment, not a guarantee of correctness or safety or a professional certification. Submitting does not guarantee a reviewer.
You do not have to be an expert. If you have experience in a domain, share it. A mathematician may need a lawyer's perspective, a chess player a visual designer, or an astrophysicist a medical professional. Say what you can assess and where your knowledge ends.
Check existing work where it matters to your question. Ask your AI assistant to look for tools for a software build, prior research for a research proposal, or relevant published guidance for a document. A software-catalogue search is not a condition of asking for feedback. Check existing work
Not a coder? Neither am I. Ask your AI assistant to guide you
Copy the message below into the AI assistant you already use: it asks your AI to explain Crossreview first, find out whether you want a review, want to give one or only want to look, and guide you through GitHub one step at a time. Your work can be a document, guide or plan rather than software, and the message asks your AI to show you every upload or post before it happens. Everything submitted here is public, so use a public, fictional or redacted example rather than client, patient, pupil or employer material, and take the same care with anything you give your AI.
Share a public GitHub repository (a public project folder; documents are fine), what it claims to do, the AI tools used and the problems you already know about.
An automatic pre-check reads supported text and code files within its size limits without running anything. It needs a README and looks for selected credential patterns. It does not read PDF, Word, spreadsheet or image contents, look for personal information, or establish correctness or security.
Choose a project in your domain if you can. Other perspectives are welcome. Mark it as picked up, then review each claim with a quote or a location such as a file and line or a page.
Your first submission needs no earlier review. After that, give one review of someone else's work for each new submission.
Explain the project's purpose, what you want checked and the problems you already know about. You decide what to change after reviewing the findings.
Match the review to the work: a protocol needs its method checked; a tool needs its behaviour checked. Report evidence and limits. If AI helps, use a different vendor from the maker; that alone does not establish independence.
See who has picked up a project before joining in. Reviewers may share their domain experience to help readers weigh their perspective. It is optional and self-described; the evidence still matters.
Loading submissions...
Loading reviews...