LlamaIndex plugins

Build and deploy production-grade LLM applications with LangGraph for agent orchestration, advanced RAG pipelines leveraging vector and hybrid search, prompt engineering patterns, and automated evaluation. Covers embedding model selection, vector index optimization, and multi-agent architectures for document Q&A, chatbots, and semantic search over proprietary data.

Build and evaluate production-grade AI agents using LangGraph, RAG systems, MCP servers, and prompt engineering patterns—with behavioral testing and reliability monitoring.

Explain machine learning model predictions using SHAP, LIME, and feature importance to identify influential features and debug behavior. Generate production-ready AI/ML code from context, including validation, error handling, performance metrics, insights, artifacts, and documentation.

Provides agent skills for comprehensive Neo4j database management: querying, modeling, data ingestion, AI/ML pipelines (GraphRAG, embeddings), graph algorithms, provisioning, security, and performance tuning.

End-to-end AI/ML workflows on DataRobot: train AutoML models, engineer features, deploy to production with CI/CD, monitor drift, explain predictions, and instrument external agents with OpenTelemetry observability.

Add persistent memory and personalization to AI applications with semantic search, guided memory recall, and automatic context management for Claude workflows.

Build production-grade LLM apps in Python: implement RAG pipelines with embeddings and hybrid search, design LangChain/LangGraph agents, optimize prompts, tune vector indexes, and evaluate performance using AI agents, skills, and commands for architecture, code gen, and benchmarking.

Add Opik observability to LLM applications: auto-detect frameworks, trace execution flows, evaluate agent reliability, and monitor production performance with session telemetry controls for Claude Code.

Automate Brazilian legal workflows: analyze civil/criminal processes, draft judicial decisions, calculate CPC/CPP deadlines, download PJe case files as PDFs or separate documents, extract text from scanned legal PDFs via OCR, search unified CJF jurisprudence, and generate executive procedural reports in DOCX/PDF with institutional styling.

Build production-ready LLM applications by delegating to expert AI agents that engineer prompts, manage dynamic contexts with vector DBs and knowledge graphs, optimize single and multi-agent performance, and orchestrate RAG, multimodal, and enterprise AI workflows.

Convert docs, repos, PDFs, videos, and more into AI-ready skill packages for LLM platforms like Claude, OpenAI, and Gemini, with auto-detection of source types and configurable preset levels.