I build AI products from problem framing to shipped workflow, with a focus on agentic systems, prompt quality, and evaluation discipline.
- LLM product strategy and execution
- Agent workflows (multi-model orchestration)
- Prompt engineering and iterative refinement
- Evaluation frameworks for quality, reliability, and safety
- indegenge_persona
- brainstorming_agent
- a2a_agent
- prompt_refiner
- MF_return_tracker
- youtube_summary
- Start from user problem and business impact
- Define measurable AI quality criteria before launch
- Ship fast prototypes and harden with evals and instrumentation
- Make trade-offs explicit in documentation
Profile updated on 2026-03-08.


