Sherwood's Digital Twin

Sherwood's Digital Twin

Chat with my AI counterpart

Sherwood

Hello! I'm Sherwood's AI Assistant

What would you like to know about Sherwood

Education

University of Central Florida

Bachelor of Science, Computer Science

UT Austin, McCombs School of Business

AI and Machine Learning: Business Applications (currently enrolled)

DataScienceDojo & University of New Mexico

Agentic AI Bootcamp

Certificates

  • The Complete Agentic AI and MCP Course
  • LLM Engineering, RAG, QLoRA, Agents
  • Deploy LLMs and Agents at Scale
  • Create Agents, Voice Agents, and Automations with n8n
  • Complete Claude Code and Coding Agents
  • Master Vector Database with Python for AI & LLM Use Cases
  • Working with Microservices in Go
  • Prometheus

AI Projects

1

Implemented a custom AI solution to perform appraisals for the oil and gas industry. Investors in oil and gas wells must produce an appraisal report to determine the value of their investments in these wells. This process is typically performed by a human expert but takes several hours and typically days of manual labor. This AI agent is able to reduce this effort down to a couple of hours or less.

2

Conducted exploratory data analysis on a food aggregator's online order data to answer key business questions posed by the Data Science team. Uncovered insights into restaurant demand and customer behavior to support data-driven decision aimed at improving customer experience.

3

Built a classification model for a fictional bank to identify liability customers with a high probability of purchasing personal loans, enabling the marketing team to target prospects more effectively and improve campaign conversion rates beyond the previous 9% benchmark.

4

Built, tuned, and evaluated classification models on 25,000 ciphered wind turbine sensor records (40 features) to predict generator failures, selecting the best model under an asymmetric cost framework that prioritized minimizing replacement costs over inspection and repair costs.

5

Built a functional RAG-based AI prototype that retrieves and synthesizes information from renowned medical manuals to support healthcare professionals in diagnosis and treatment planning. Evaluated its impact on reducing information overload, accelerating time-sensitive decisions, and standardizing care practices, demonstrating the feasibility of grounded clinical AI assistants for real-world use.