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 35 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.
Initialize a CrewAI project. Define at least three agents with distinct roles for a 'Scientific Review Board': a 'Factual Verifier', a 'Consistency Checker', and an 'AI Slop Detector'. Assign each agent a goal and a backstory. Configure them to use Claude Opus 4.1 as their primary LLM. Provide the Python code for agent setup.
```python
from crewai import Agent, Task, Crew, Process
from langchain_anthropic import ChatAnthropic # Use specific Langchain integration for Claude
# Initialize Claude Opus 4.1 LLM
claude_opus_llm = ChatAnthropic(model="claude-3-opus-20240229", temperature=0.2, anthropic_api_key="YOUR_ANTHROPIC_API_KEY")
# Factual Verifier Agent
factual_verifier = Agent(
role='Factual Verifier',
goal='Verify the factual accuracy of claims in scientific texts against established knowledge.',
backstory='An meticulous researcher with access to vast scientific databases, ensuring every statement is evidence-backed.',
verbose=True,
allow_delegation=False,
llm=claude_opus_llm
)
# Consistency Checker Agent
consistency_checker = Agent(
role='Consistency Checker',
goal='Identify logical inconsistencies, contradictions, and methodological flaws within a scientific document.',
backstory='A sharp-eyed critic who ensures coherence and methodological rigor in scientific discourse.',
verbose=True,
allow_delegation=True,
llm=claude_opus_llm
)
# AI Slop Detector Agent
ai_slop_detector = Agent(
role='AI Slop Detector',
goal='Detect generic phrasing, vague claims, repetitive patterns, and other hallmarks of low-quality, potentially AI-generated text.',
backstory='A seasoned editor with an uncanny ability to spot superficial writing and lack of original thought, especially from generative models.',
verbose=True,
allow_delegation=False,
llm=claude_opus_llm
)
# (Tasks and Crew definition will follow)
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.
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.