Writing · 4 posts
Notes from building AI systems that have to work in real time.
What I built, what I measured, and what broke. Follow along by RSS.
Featured
Where the latency goes in a local voice agent
A stage-by-stage breakdown of a local voice agent's turn, with measured numbers: speech recognition is cheap, endpointing and the model's first sentence are not.
21 Oct 2026 · 6 min read
Featured
Barge-in is a policy problem, not a model problem
Two-stage barge-in, echo gating and an interviewer's turn-taking rules: why interruptions in voice agents are state-machine code that deserves ordinary tests.
19 Oct 2026 · 6 min read
2026
Where the latency goes in a local voice agent
A stage-by-stage breakdown of a local voice agent's turn, with measured numbers: speech recognition is cheap, endpointing and the model's first sentence are not.
· 6 min read · voice ai, latency, speech recognition
Barge-in is a policy problem, not a model problem
Two-stage barge-in, echo gating and an interviewer's turn-taking rules: why interruptions in voice agents are state-machine code that deserves ordinary tests.
· 6 min read · voice ai, turn-taking, barge-in
Letting an LLM agent touch a real database safely
How Agent2DB handles large schemas and dangerous writes: a ranked schema index, three layers of write safety, durable approvals and budgets on every run.
· 6 min read · agents, langgraph, postgresql
Swap a hosted model API for a local one without touching the client
A Qwen3 reranker behind a Cohere-compatible /v2/rerank and Kokoro TTS behind OpenAI's /v1/audio/speech: copying an API contract so migration is a base-URL change.
· 5 min read · rag, reranking, tts