AI Engineer — prompt systems, agentic AI.
I build reliable LLM workflows: evaluation pipelines, and agent automation.
Background in ML data quality and LLM evaluation.
- prompt-engineering-studio — local-first workspace for prompt design and evals with 70+ prompting techniques.
- system-prompt-benchmark — security testing across attack vectors (injection, jailbreaks, leakage).
- dspy-optimization-patterns — teacher-student optimization patterns for quality/cost trade-offs (up to 50x cost reduction).
- synth-dataset-kit - CLI tool for generating high-quality synthetic datasets for LLM fine-tuning.
- NovelGenerator — autonomous multi-agent fiction pipeline.
- browser-agent-chrome-extension — Claude-like Chrome browser agent focused on cost-efficient automation.
- llmflow-search — deep research agent that synthesizes reports from multiple web sources.
- vision-agent-analyst — multimodal analysis for charts, UI screenshots, and PDFs.
Python TypeScript DSPy RAG Prompt Engineering LLM Evals Agentic Workflows