Skip to content

chore: remove unused OPTIMIZATION_OBJECTIVE constant #14160

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
detail-app merged 1 commit into from
Sep 9, 2026
Merged

chore: remove unused OPTIMIZATION_OBJECTIVE constant #14160

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 0 additions & 16 deletions server/polar/organization_review/eval/optimize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -208,22 +208,6 @@ def make_reflective_dataset(
# Dataset helpers
# ---------------------------------------------------------------------------

OPTIMIZATION_OBJECTIVE = """\
Optimize the compliance review system prompt for a Merchant of Record platform. \
The prompt instructs an LLM to review organizations applying to sell digital products.

The dataset contains cases where the AI incorrectly APPROVED organizations that \
human reviewers later DENIED. These are the most dangerous errors — they let \
risky organizations onto the platform.

Goal: modify the prompt so the AI correctly DENIES these organizations while \
still being fair to legitimate businesses (template sellers, AI SaaS, content \
creation tools, digital education).

The Feedback field in reflective data includes human reviewer reasoning — use \
it to understand patterns the current prompt misses.\
"""


def _cases_to_gepa_format(cases: list[Any]) -> list[dict[str, Any]]:
"""Convert pydantic-evals Cases to the dict format GEPA expects."""
Expand Down
Loading