Back to Prompt Library
implementation
Initial CrewAI Setup and Agent Role Definition
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Misinformation Debunking Team
Format
Code-aware
Lines
56
Sections
11
Linked challenge
Misinformation Debunking Team
Prompt source
Original prompt text with formatting preserved for inspection.
56 lines
11 sections
No variables
1 code block
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 change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.