Measuring whether an AI system is actually getting better — with numbers, not impressions.
Every serious system I build carries an eval set. It turns 'this prompt feels better' into a number, and it's what lets a team change models, prompts or quantization without fear.
Product engineering teams
A domain eval set with automated scoring, wired into the delivery pipeline, so a prompt change, model swap or new quantization can't ship if it makes the task worse. It turned “it feels better” into a number the team could discuss.
Contact
I'm open to AI engineering, architecture and training work. Tell me what you're building and what the constraints are — that's usually enough to start.