Skip to content

Add AI coding assistant policy for candidates#2

Open
ahue-ifco wants to merge 1 commit intomainfrom
docs/ai-coding-assistant-policy
Open

Add AI coding assistant policy for candidates#2
ahue-ifco wants to merge 1 commit intomainfrom
docs/ai-coding-assistant-policy

Conversation

@ahue-ifco
Copy link
Copy Markdown
Contributor

Summary

  • Adds a new "On the Use of AI Coding Assistants" section to the README
  • Makes PROMPTS.md submission mandatory — missing it leads to rejection
  • Requires a candidate-written REVIEW.md documenting corrections to AI output
  • Sets expectation that candidates must defend all modeling decisions in the interview

Test plan

  • Review rendered README on GitHub for formatting
  • Confirm section placement reads naturally after "Additional Instructions"

🤖 Generated with Claude Code

Clarify expectations around agentic tool usage: require candidate-written
REVIEW.md, make PROMPTS.md mandatory (rejection on missing), and set
expectations for defending AI-assisted decisions in interviews.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR adds a new "On the Use of AI Coding Assistants" policy section to the README, establishing clear expectations for how candidates should document their use of AI tools during the challenge. The section encourages thoughtful use of AI coding assistants while requiring transparency and accountability through mandatory documentation and interviews.

Changes:

  • Adds a new policy section establishing guidelines for AI coding assistant usage
  • Makes PROMPTS.md submission mandatory with rejection for non-compliance
  • Requires candidates to submit a REVIEW.md documenting their critical evaluation of AI-generated code
  • Sets expectation that candidates must defend all modeling decisions in interviews

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

You are welcome to use agentic coding tools (Copilot, Claude Code, Cursor, etc.) — in fact, effective use of these tools is a valuable skill. However:

- Include a `REVIEW.md` **written entirely by you** documenting where the agent's output required correction, what you changed, and why. This must reflect your own critical thinking — we evaluate your judgment, not the agent's output. AI-generated reviews defeat the purpose and will be apparent.
- **The `PROMPTS.md` file is mandatory.** Include your full prompt chain. Submissions without a `PROMPTS.md` will be rejected, regardless of solution quality.
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think will be impractical to collect (or even process by us) all the chain of prompting if the candidate is a heavy user.

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Fair, still would want it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants