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.
What you are building
The core problem, expected build, and operating context for this challenge.
Build a multi-agent team using CrewAI and OpenAI o4o to fact-check misinformation, verify sources, and generate evidence-based debunking reports.
How work is evaluated
The evaluation will assess the CrewAI team's ability to accurately identify misinformation, provide credible evidence, maintain neutrality, and generate comprehensive debunking reports. Collaboration efficiency and error handling will also be considered.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
CorrectMisinformationIdentification
The team must correctly identify whether misinformation is present in the post.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
SourceCredibility
All cited sources must be recognized as credible (e.g., from a predefined list of reputable sources).
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
FactualAccuracyScore
Automated assessment of the factual correctness of the debunking report. • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
CollaborationEfficiency
Number of sequential agent turns to complete the task, indicating efficient workflow. • target: 5 • range: 2-10
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Master CrewAI for defining agent roles, tasks, and collaborative processes in a multi-agent workflow.
Implement OpenAI o4o for advanced reasoning, natural language understanding, and tool execution within individual agents.
Design custom tools for agents to interact with external services, including a vector database (Weaviate) for semantic search over a curated knowledge base of facts and sources.
Orchestrate a task flow where agents collaborate to analyze social media posts, cross-reference facts, identify logical fallacies, and synthesize a coherent debunking narrative.
Utilize Factory AI concepts for deploying, managing, and scaling multiple CrewAI teams as part of a larger enterprise misinformation detection platform.
Integrate LangSmith for end-to-end tracing of agent conversations, tool calls, and decision pathways to debug and optimize collaborative performance.
Develop robust evaluation metrics for fact-checking accuracy, source credibility, and report neutrality.
Reference links and supporting material
Sample data for 1 tasks
Challenge setup
The evaluation will assess the CrewAI team's ability to accurately identify misinformation, provide credible evidence, maintain neutrality, and generate comprehensive debunking reports. Collaboration efficiency and er...
Challenge input
{ "social_media_post": "string", "context_data": "object" }
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{ "misinformation_identified": "boolean", "claims_to_debunk": "array<string>", "debunking_report": "string", "sources_cited": "array<string>", "age...
- The team must correctly identify whether misinformation is present in the post.
- All cited sources must be recognized as credible (e.g., from a predefined list of reputable sources).
- Automated assessment of the factual correctness of the debunking report. • target: 0.95 • range: 0-1
- FactualAccuracyScore target: 0.95
- 1 public reference case
- Python execution harness
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- CorrectMisinformationIdentification · Weight 1
- SourceCredibility · Weight 1
- FactualAccuracyScore · Weight 1
- CollaborationEfficiency · Weight 1
Metrics
- FactualAccuracyScore · Target 0.95
- CollaborationEfficiency · Target 5
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: { "social_media_post": "string", "context_data": "object" }
Output: { "misinformation_identified": "boolean", "claims_to_debunk": "array<string>", "debunking_report": "string", "sources_cited": "array<string>", "agent_collaboration_log": "array<string>" }
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.