Deconstructing AI Prose Quirks
The subtle 'quirks' in AI-generated prose, often a result of 'overfitting,' are increasingly being mimicked by human writers, blurring the lines of textual authenticity. This challenge tasks you with building a sophisticated multi-agent system using Gemini 3 Pro and Langroid to perform linguistic forensics, accurately identifying AI-generated content, human-mimicking-AI content, and purely human writing. Your system will employ A2A protocol for collaborative analysis, leveraging Gemini 3 Pro's Deep Think mode for profound semantic and stylistic insights. Agents will adapt their thinking budgets based on the complexity of the text, providing detailed reports on characteristic AI linguistic patterns and suggesting 'de-AI-ification' strategies to restore human-like prose, effectively becoming a 'prose purity' guardian.
What you are building
The core problem, expected build, and operating context for this challenge.
The subtle 'quirks' in AI-generated prose, often a result of 'overfitting,' are increasingly being mimicked by human writers, blurring the lines of textual authenticity. This challenge tasks you with building a sophisticated multi-agent system using Gemini 3 Pro and Langroid to perform linguistic forensics, accurately identifying AI-generated content, human-mimicking-AI content, and purely human writing. Your system will employ A2A protocol for collaborative analysis, leveraging Gemini 3 Pro's Deep Think mode for profound semantic and stylistic insights. Agents will adapt their thinking budgets based on the complexity of the text, providing detailed reports on characteristic AI linguistic patterns and suggesting 'de-AI-ification' strategies to restore human-like prose, effectively becoming a 'prose purity' guardian.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master Langroid for orchestrating conversational multi-agent systems, enabling agents to discuss and refine their linguistic analyses.
Leverage Gemini 3 Pro's Deep Think mode to conduct profound semantic and stylistic analysis, identifying subtle AI-generated prose quirks and 'overfitting' patterns.
Implement the A2A protocol for secure, asynchronous communication between specialized agents (e.g., Stylistic Analyzer, Semantic Inspector, Human-AI Discriminator).
Develop adaptive thinking budgets for agents, allowing them to allocate more computational resources (tokens, processing time) for challenging or ambiguous text samples.
Integrate OpenAI o3 as a 'fast-pass' agent for initial screening and less complex texts, optimizing overall system efficiency.
Design tools within Semantic Kernel to identify and suggest modifications for AI-generated stylistic redundancies, clichés, or syntactic patterns to 'de-AI-ify' text.
Build a robust data pipeline to collect and categorize examples of AI prose, human-mimicking-AI, and pure human text for training and evaluation.
How this agent runs
Evaluation will assess the system's ability to accurately classify text origins and provide insightful linguistic analysis. It will also examine the efficiency of A2A communication and adaptive budget utilization.
Challenge input
{'texts': [{'id': '1', 'content': 'sample text 1'}, {'id': '2', 'content': 'sample text 2'}...]}
Agent execution
The configured agent processes the input under the challenge policy.
Evaluated output
{'analyses': [{'id': '1', 'origin': 'AI-generated', 'confidence': 0.9, 'quirks': ['formulaic phrasing', 'lexical redundancy']}, ...]}
- Verify that agents communicate effectively using the A2A protocol, exchanging analysis results and insights.
- Confirm that the system intelligently adjusts reasoning budgets based on text complexity, using Deep Think...
- Classification Accuracy target: 0.9
- Python execution harness
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- The evaluation module defines the checks.
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset
Versalist can run this agent on your behalf with your data. Tell us about your dataset and the result you need.
Discuss your dataset[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.