Skip to content

Conversation

@geoffreyjing
Copy link

📝 Summary

added prompt comparison cookbook

✅ Checklist

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @geoffreyjing, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request enhances the project's README.md by integrating a new 'Prompt Comparisons' entry into the existing cookbook table. This addition provides users with a direct link to a Colab notebook focused on evaluating and scoring different customer support prompts, thereby improving resource accessibility for prompt engineering tasks.

Highlights

  • Documentation Update: The README.md file has been updated to include a new entry in the 'Cookbooks' section, specifically for 'Prompt Comparisons'.
  • New Cookbook Link: A link to a new Colab notebook, 'Customer Support Agent', has been added, demonstrating how to test and score customer support prompts.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request updates the README.md to add a new cookbook for prompt comparisons. The changes are straightforward, but I have a couple of suggestions to improve formatting and consistency. One comment addresses excessive blank lines, and the other suggests aligning the new cookbook's link with the established structure for other cookbooks in the repository. Applying these suggestions will improve the document's readability and maintainability.

README.md Outdated
Comment on lines 10 to 11


Copy link
Contributor

Choose a reason for hiding this comment

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

medium

These extra blank lines are unnecessary. Removing them will improve the document's formatting and readability.

README.md Outdated
| Online ABM | [Research Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/monitoring/Research_Agent_Online_Monitoring.ipynb) | Monitor agent behavior in production |
| Custom Scorers | [HumanEval](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/custom_scorers/HumanEval_Custom_Scorer.ipynb) | Build custom evaluators for your agents |
| Offline Testing | [Get Started For Free] | Compare how different prompts, models, or agent configs affect performance across ANY metric |
| Prompt Comparisons | [Customer Support Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/JudgmentCustomScorer.ipynb) | Test and score customer support prompts to see which style performs best |
Copy link
Contributor

Choose a reason for hiding this comment

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

medium

For consistency with other cookbooks in the table, this notebook should be placed in a subdirectory that matches its category and have a filename that reflects its content. The current path and filename are inconsistent with the established pattern in this project. Please see the suggestion for a more consistent link.

Suggested change
| Prompt Comparisons | [Customer Support Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/JudgmentCustomScorer.ipynb) | Test and score customer support prompts to see which style performs best |
| Prompt Comparisons | [Customer Support Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/prompt_comparisons/Customer_Support_Agent.ipynb) | Test and score customer support prompts to see which style performs best |

Copy link
Collaborator

Choose a reason for hiding this comment

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

Do this

@JCamyre JCamyre changed the base branch from main to staging November 15, 2025 21:58
Removed extra blank lines in README.md
Copy link
Collaborator

@JCamyre JCamyre left a comment

Choose a reason for hiding this comment

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

Check gemini comment

README.md Outdated
| Online ABM | [Research Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/monitoring/Research_Agent_Online_Monitoring.ipynb) | Monitor agent behavior in production |
| Custom Scorers | [HumanEval](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/custom_scorers/HumanEval_Custom_Scorer.ipynb) | Build custom evaluators for your agents |
| Offline Testing | [Get Started For Free] | Compare how different prompts, models, or agent configs affect performance across ANY metric |
| Prompt Comparisons | [Customer Support Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/JudgmentCustomScorer.ipynb) | Test and score customer support prompts to see which style performs best |
Copy link
Collaborator

Choose a reason for hiding this comment

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

Do this

@propel-code-bot
Copy link

✔️ Propel has finished reviewing this change.

Copy link
Collaborator

@JCamyre JCamyre left a comment

Choose a reason for hiding this comment

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

Requests

| RL | [Wikipedia Racer](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/rl/WikiRacingAgent_RL.ipynb) | Train agents with reinforcement learning |
| Online ABM | [Research Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/monitoring/Research_Agent_Online_Monitoring.ipynb) | Monitor agent behavior in production |
| Custom Scorers | [HumanEval](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/custom_scorers/HumanEval_Custom_Scorer.ipynb) | Build custom evaluators for your agents |
| Offline Testing | [Get Started For Free] | Compare how different prompts, models, or agent configs affect performance across ANY metric |
Copy link
Collaborator

Choose a reason for hiding this comment

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

Two things:

  1. Comment the Offline testing row out - please make a Linear task to make one, assign to yourself for now
  2. Make your Customer_Support_Agent.ipynb notebook public (i.e. share -> anyone with link can view)

Copy link
Author

Choose a reason for hiding this comment

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

I think the notebook should already be public, just tried opening it in an incognito tab and was able to see it

commented out offline testing
| RL | [Wikipedia Racer](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/rl/WikiRacingAgent_RL.ipynb) | Train agents with reinforcement learning |
| Online ABM | [Research Agent](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/monitoring/Research_Agent_Online_Monitoring.ipynb) | Monitor agent behavior in production |
| Custom Scorers | [HumanEval](https://colab.research.google.com/github/JudgmentLabs/judgment-cookbook/blob/main/custom_scorers/HumanEval_Custom_Scorer.ipynb) | Build custom evaluators for your agents |
<!--

Choose a reason for hiding this comment

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

[Documentation]

The standalone HTML comment lines interrupt the Markdown table, so the new “Prompt Comparisons” row renders outside the table. Please move the comment onto a single line with the row (e.g., <!-- | Offline Testing ... | -->) or remove it so the table remains contiguous.

Context for Agents
[**Documentation**]

The standalone HTML comment lines interrupt the Markdown table, so the new “Prompt Comparisons” row renders outside the table. Please move the comment onto a single line with the row (e.g., `<!-- | Offline Testing ... | -->`) or remove it so the table remains contiguous.

File: README.md
Line: 64

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