Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 22 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Create a Python tool that allows the 'Factual Verifier' agent to query a Pinecone vector database. Assume the database is pre-populated with embeddings of scientific articles/facts. The tool should take a query string (a claim from the text) and return relevant supporting or contradicting documents. Provide the tool definition and how to integrate it with the `Factual Verifier` agent.
```python
from crewai_tools import BaseTool
from pinecone import Pinecone, ServerlessSpec
# from your_embedding_model_library import get_embedding # e.g., from an API or a local Mistral Saba model
# Initialize Pinecone (replace with your actual API key and environment)
# pc = Pinecone(api_key="YOUR_PINECONE_API_KEY", environment="YOUR_PINECONE_ENVIRONMENT")
# index = pc.Index("scientific-facts") # Assume an index exists
class PineconeFactCheckerTool(BaseTool):
name: str = "Pinecone Fact Checker"
description: str = "Searches a Pinecone vector database for scientific facts to verify claims."
def _run(self, query: str) -> str:
# query_embedding = get_embedding(query) # Replace with actual embedding call
query_embedding = [0.1] * 768 # Placeholder
# Example Pinecone search
# results = index.query(vector=query_embedding, top_k=3, include_metadata=True)
# formatted_results = [f"Fact: {match.metadata['text']} (Score: {match.score:.2f})" for match in results.matches]
# return "\n".join(formatted_results) if formatted_results else "No relevant facts found."
return f"Simulated Pinecone search for '{query}' returned: Fact X and Fact Y."
# Add the tool to the Factual Verifier agent
# factual_verifier.tools.append(PineconeFactCheckerTool())
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Hold the task contract and output shape stable so generated implementations remain comparable.
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
Orchestrate Scientific Integrity Agent Crew
With growing concerns about 'AI slop' in scientific publishing, this challenge focuses on developing an agentic system to enforce scientific integrity. You will use CrewAI to orchestrate a team of specialized AI agents that act as a 'Scientific Review Board.' This crew will collaborate to analyze newly generated scientific abstracts or summaries, identify potential factual inaccuracies, inconsistencies, and characteristics of AI-generated content, and verify claims against a knowledge base. The system should highlight suspicious areas and provide justifications for its findings, leveraging the advanced reasoning capabilities of Claude Opus 4.1.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.