Play 77
Research Paper AI
AI-powered academic research — literature review, citation analysis, and research gap identification.
AI-powered academic research assistant automating literature review, citation network analysis, methodology critique, and research gap identification. Azure AI Search indexes paper abstracts and full texts with semantic ranking, OpenAI analyzes methodology quality and identifies contradictions across studies, Microsoft Graph connects institutional knowledge bases, Cosmos DB stores citation networks and analysis results, and Functions orchestrate multi-paper analysis workflows.
Architecture Pattern
RAG + citation graph: paper ingestion → semantic search → methodology analysis → gap identification → synthesis
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Research Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (217 lines), evaluate (126 lines), tune (236 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + Semantic Scholar inputs + envFile
TuneKit (AI Config)
- config/openai.json — analysis and synthesis prompts
- config/research.json — citation databases, methodology frameworks, domain taxonomy
- config/guardrails.json — academic integrity, citation accuracy
- evaluation/eval.py — Citation accuracy >95%, Gap identification precision >80%
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.