Back to Prompt Library
testing

Relicx Eval Integration

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: GPT-5.4 Pro Bio-Research Agent with Pydantic AI Validation

Format
Text-first
Lines
1
Sections
1
Linked challenge
GPT-5.4 Pro Bio-Research Agent with Pydantic AI Validation

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Create a script that sends 100 agent-generated biological summaries to Relicx for scoring against a set of known scientific ground truths using the Relicx evaluation API.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the rubric, target behavior, and pass-fail criteria as the baseline for evaluation.

Tune next

Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.

Verify after

Make sure the prompt catches regressions instead of just mirroring the happy-path examples.