Notes from the build floor.
Long-form write-ups on evals, retrieval, voice latency budgets, cost control, and the operating model behind agents that stick.
Evals Before Demos: How We Scope an Agent Build
Why we refuse to write agent code before writing the eval set — and the exact template we use with clients in week one.
Agentic RAG in Production: Retrieval Isn't the Hard Part
Chunking, reranking, and citation UX matter less than the boring plumbing: freshness, access control, and failure fallbacks.
Voice Agents and the 300ms Budget
A latency-first architecture for phone-grade voice: streaming STT, partial LLM, and TTS interleave — with real numbers.
The AI Operating Model for a 10-Person Startup
You don't need an AI team. You need three habits: an eval loop, a prompt registry, and a weekly incident review.
Cutting Agent Cost 8x Without Touching the Prompt
Router models, caching, structured outputs, and the one line of code that saved a client $14k/month.
AI for Solopreneurs: The 5 Workflows That Pay for Themselves in a Week
Inbox triage, proposal drafting, meeting recap, lead research, and content repurposing — with off-the-shelf tools.