3. Data, Science & AI

Performs panel data analysis in Python using linearmodels for econometric modeling and pandas for data manipulation.

Fetches economic data from FRED, World Bank, and other APIs for data analysis and processing.

Creates publication-ready regression tables in LaTeX format for academic and scientific data presentation.

Generates publication-quality charts and graphs for economic data analysis and academic papers.

Runs regression analyses in Stata and produces publication-ready statistical output tables for research reporting.

Automates data cleaning and transformation workflows in Stata, ensuring reproducibility for statistical analysis.

Provides persistent memory storage and recall for AI agents across sessions, eliminating session-based amnesia and enhancing context retention.

Serves as the default system prompt for consistent AI behavior across all interactions, ensuring context-aware responses.

Enables creation, editing, and analysis of spreadsheets with formula support, formatting, and data visualization for structured data tasks.

Analyzes meeting transcripts and recordings using AI to identify communication patterns and provide actionable feedback for professional development.

Expert prompt engineering for AI systems, including writing, reviewing, and optimizing prompts for LLMs like Claude and GPT to enhance AI performance and output quality.

Provides design principles for AI agent tools including naming, input/output structure, error handling, and evaluation to maximize agent effectiveness.

Graph-first memory orchestration with knowledge graph primary and optional mem0 cloud for semantic search in AI applications.

Validates golden datasets for AI evaluation through schema checks, duplicate detection, and coverage analysis to ensure data integrity.

Provides reusable patterns for cross-encoder reranking and LLM-based relevance scoring to enhance search precision in RAG pipelines.

Optimizes LLM agent prompts and RAG systems to reduce token usage while preserving quality through strategic context design.

Provides parallel execution patterns for LangGraph, enabling fan-out/fan-in workflows, map-reduce, and concurrent agent execution in AI applications.

Enables human-in-the-loop interactions in AI agent workflows using LangGraph, supporting approval processes, manual reviews, and user feedback integration.

Enables safe, zero-downtime database schema migrations using the expand-contract pattern for seamless production deployments.

Guides selection and implementation of multi-agent frameworks beyond LangGraph, including CrewAI, Microsoft Agent Framework, and OpenAI Agents SDK for AI agent development.

Tracks LLM cost savings from caching using Langfuse, monitoring cache effectiveness and attributing costs to agents in multi-agent systems.

Provides LLM observability for tracing, evaluation, prompt management, and cost tracking to optimize AI model usage.

Enables building central coordinator agents that route tasks to specialized workers using round-robin or priority-based dispatch in LangGraph.

Provides advanced RAG patterns for agentic pipelines, including Self-RAG, Corrective-RAG, and knowledge graphs for adaptive retrieval and query rewriting.