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 56 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.
Set up a new CrewAI project. Define three agents: a 'Source Verifier' (role: verifying information against credible sources), a 'Content Analyzer' (role: identifying logical fallacies and inflammatory language), and a 'Report Generator' (role: synthesizing findings into a neutral report). Assign OpenAI o4o as the LLM for all agents. Define initial tasks for each agent and orchestrate a simple sequential process where the Verifier checks a claim, Analyzer reviews it, and Generator drafts a summary.
```python
# crew_main.py
from crewai import Agent, Task, Crew, Process
from langchain_openai import ChatOpenAI
# Initialize your OpenAI LLM
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.7) # Using mini for example, use gpt-4o for full power
# Define Agents
source_verifier = Agent(
role='Source Verifier',
goal='Verify factual claims against established credible sources.',
backstory='An expert in journalistic integrity and digital forensics.',
llm=llm,
verbose=True,
allow_delegation=False
)
content_analyzer = Agent(
role='Content Analyzer',
goal='Identify logical fallacies, emotional appeals, and misleading rhetoric in content.',
backstory='A linguist and critical thinking specialist.',
llm=llm,
verbose=True,
allow_delegation=True
)
report_generator = Agent(
role='Report Generator',
goal='Synthesize verified information into a neutral, evidence-based debunking report.',
backstory='A skilled technical writer and communicator.',
llm=llm,
verbose=True,
allow_delegation=False
)
# Define Tasks (initial simple tasks)
verify_task = Task(
description='Analyze the claim: "COVID-19 was caused by 5G towers" and find credible sources.',
agent=source_verifier
)
analyze_task = Task(
description='Review the claim and any findings from the Source Verifier. Identify rhetorical tactics.',
agent=content_analyzer
)
generate_task = Task(
description='Based on verified facts and analysis, draft a neutral debunking statement.',
agent=report_generator
)
# Form the crew
crew = Crew(
agents=[source_verifier, content_analyzer, report_generator],
tasks=[verify_task, analyze_task, generate_task],
process=Process.sequential,
verbose=2
)
# Kick off the crew's work
# result = crew.kickoff()
# print(result)
```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.
Misinformation Debunking Team
In response to the pervasive issue of fabricated content and misdirection on social media, this challenge involves building a sophisticated multi-agent system using CrewAI. Your task is to design a team of specialized AI agents to collaboratively debunk misinformation, verify facts, and synthesize neutral, evidence-based reports. The team will be powered by OpenAI o4o for its multimodal reasoning and advanced tool-use capabilities. Each agent within the CrewAI team will have a distinct role (e.g., 'Source Verifier', 'Content Analyzer', 'Report Generator') and will utilize specific tools, including a vector database like Weaviate for rapid semantic search over verified knowledge bases. The system must be capable of processing social media content, identifying false claims, citing credible sources, and producing comprehensive reports, while its operational transparency and performance are monitored and evaluated through LangSmith.
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.