docs: add LLM-as-Judge examples and repo guidance - #2
Merged
Conversation
Add standalone live examples that show RAG scoring, batch decisions, model comparison, custom metrics, and Minitest assertions without expanding the root README. Bump the gem version for the example release while keeping the examples excluded from packaged gem files. Constraint: Keep root README unchanged; examples live separately Constraint: Examples should remain outside packaged gem files Rejected: Package examples in the gem | demo scripts increase installed payload without runtime value Confidence: high Scope-risk: narrow Directive: Keep live provider-call examples outside the root README and outside packaged gem files unless release policy changes Tested: bundle exec rake Tested: ruby -e spec package check reported version=0.1.2 and examples_in_package=[] Tested: gem build rubric_llm.gemspec --output /tmp/rubric_llm-0.1.2.gem Tested: git diff --cached --check Not-tested: Live provider example scripts; they require OpenAI API calls
dpaluy
force-pushed
the
chore/examples-pr
branch
from
April 30, 2026 04:05
437bf39 to
d6217ed
Compare
Bring the examples PR back to the intended full scope: include repository agent guidance, ignore local OMX workflow state, update the README quick-start judge model to gpt-5.5, and point readers to the standalone examples. Constraint: Keep a single PR containing README, .gitignore, AGENTS.md, and examples changes Constraint: Do not commit .omx workflow state Confidence: high Scope-risk: narrow Directive: Keep .omx ignored as local workflow/session state Tested: bundle exec rake Tested: ruby -e package check reported version=0.1.2, examples_in_package=[], agents_in_package=[] Tested: git diff --check Not-tested: Live provider example scripts; they require OpenAI API calls
dpaluy
force-pushed
the
chore/examples-pr
branch
from
April 30, 2026 04:08
d6217ed to
ecc73f0
Compare
Add a compact outline to the standalone examples guide so readers can jump directly to setup, each runnable example, and the batch-output explanation. Constraint: Keep the examples guide detailed but easier to scan Confidence: high Scope-risk: narrow Tested: git diff --check Not-tested: Runtime examples; docs-only change
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Why
Users asked for practical LLM-as-Judge examples that are easy to demo and adapt. This PR keeps those examples separate from the main README while still linking to them, and it includes the repo-local guidance and ignore rule needed for future agent work.
Changes
docs(examples): make LLM-as-judge demos self-contained
docs: add repository guidance and examples pointer
Testing
Risk & Rollout