Missing system state, absent ownership, and the illusion of intelligence in real-world deployments.
A practical exploration of multi-agent AI for software development, built around local LLMs and specialized agent roles that can be combined into different coding crews.
Designing AI systems that respect uncertainty, accountability, and human judgment.
A follow-up to introducing Polyglot: I benchmarked it against three other coding agents on open-weight models, to check whether my core assumption was even true.
A coding-agent CLI that behaves the same whether the model is Claude, GPT, or an open-weight model running locally - because it treats tool calls as a text-parsing problem, not an API contract.
A week of real pushback on the Polyglot benchmark forced me to actually check my own work - including on myself.
My journey to build an Agentic AI solution that allows for interactive conversations about career, resume, publications, and skills.
