3. Data, Science & AI

Explains transformer concepts, chaining, and integration for event processing tasks like validation, enrichment, and redaction in data pipelines.

Creates walkerOS transformers for data validation, enrichment, or redaction using example-driven workflows.

Optimizes and designs effective prompts for LLM interactions, improving output quality and reliability in production environments.

Guides complex reasoning tasks using AI prompting techniques like Chain-of-Thought, Tree of Thoughts, and ReAct with research-backed patterns.

Assesses and refines prompt effectiveness for Claude Code agents, validating context engineering choices and measuring quality improvements in AI agent performance.

Optimizes AI agent performance through context engineering for prompts, commands, and sub-agents in agent systems.

Designs multi-agent architectures to handle complex tasks through subtask decomposition and agent specialization for enhanced performance.

Expertly crafts and refines system prompts for AI agents using Anthropic's context engineering principles to optimize performance and behavior.

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

Runs and writes Ark Chainsaw tests with mock-LLM for debugging failures and creating end-to-end tests in AI application development.

Spawns Codex subagents via background shell to offload context-heavy tasks including deep research, codebase exploration, and documentation generation.

Generates minimal file selection patterns for LLM context by analyzing codebases, optimizing retrieval efficiency in AI systems.

Automates Change Data Capture (CDC) processing in Spark pipelines for upserts, deletes, and slowly changing dimensions (SCD Type 1/2).

Comprehensive guide for building Agentic RAG systems with Microsoft Agent Framework in C#, including semantic search and multi-agent workflows.

High-performance data analysis with Polars for loading, transforming, aggregating, and visualizing tabular data in CSV/JSON/Parquet formats.

Analyzes CSV datasets, handles missing values via imputation, and generates interactive Plotly Dash dashboards for exploratory data analysis.

Generates interactive visualizations and statistical plots from CSV data for exploratory data analysis using Plotly.

Analyzes sales and revenue data from CSV files to identify weaknesses, generate statistical insights, and provide strategic business improvement recommendations.

Comprehensive personal finance management system analyzing transaction data, generating visualizations, and providing actionable financial insights and recommendations.

Provides Bayesian regression model implementations including linear, logistic, Poisson, and robust regression using Stan and JAGS.

Expertise in developing secure SQLite databases for desktop applications, including migration management, FTS search, and SQL injection prevention.

Performs statistical analysis including hypothesis testing, inference, and A/B testing for experimental validation and data-driven decision making.

Specializes in R 4.4+ development for data analysis pipelines, ggplot2 visualizations, and Shiny application building using tidyverse.

Provides Python and R programming assistance for data analysis, automation, and reproducible analytics workflows.