IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

8 articles

10 Mar 2026 · 24 min read

deployment

Production Voice AI for Research at Scale: Deployment and Go-Live — From Docker Compose to 200 Concurrent Sessions (Part 8 of 8)

Part 8 of 8 — The complete deployment guide: Docker multi-stage builds, Kubernetes orchestration, CI/CD with GitHub Actions, zero-downtime deploys, go-live checklist, production monitoring with Prometheus/Grafana, and the operational runbook that keeps voice AI running at scale.

08 Mar 2026 · 19 min read

gemini-live

Production Voice AI for Research at Scale: Multi-Language Voice AI — When Your Agent Needs to Think in Japanese (Part 7 of 8)

Part 7 of 8 — Multi-language voice AI for research: language detection, provider routing (Gemini Live for 30+ languages, OpenAI Realtime for English), locale-aware VAD tuning, i18n prompt packs, and cross-language analysis pipelines.

06 Mar 2026 · 14 min read

devops

Production Voice AI for Research at Scale: What Breaks at 200 Concurrent Sessions (Part 6 of 8)

Part 6 of 8 — Scaling from 10 sessions/week to 200 concurrent. The enrichment bottleneck (30,000 API calls), session recovery for dropped WebRTC connections, provider failover, and the operational metrics that keep it all visible.

04 Mar 2026 · 13 min read

cost-optimization

Production Voice AI for Research at Scale: The Real Cost (Part 5 of 8)

Part 5 of 6 — Real-time per-minute cost tracking, provider comparison (OpenAI Realtime ~$0.053/min vs Gemini Live ~$0.029/min), budget enforcement with soft/hard limits, and the self-hosting math that saves 90% on transport.

02 Mar 2026 · 15 min read

data-pipeline

Production Voice AI for Research at Scale: From Recording to Insight (Part 4 of 8)

Part 4 of 6 — The 3-stage automatic pipeline that turns raw interview recordings into enriched, queryable research data in 3-7 minutes. Transcription, enrichment, analysis — with the transcript batching trick that cut DB load by 80%.

28 Feb 2026 · 12 min read

agents

Production Voice AI for Research at Scale: Multi-Phase State Machines (Part 3 of 8)

Part 3 of 6 — Research interviews follow structured protocols with distinct phases. How to build an LLM-driven state machine with next_phase() function calling and dynamic instruction swapping via set_chat_ctx().

26 Feb 2026 · 13 min read

debugging

Production Voice AI for Research at Scale: Zombie Agents, Pre-Warming, and the 5 Bugs That Cost Us Weeks (Part 2 of 8)

Part 2 of 6 — The production pain points nobody warns you about: zombie agents, metadata latency, pre-warming for 1-2s time-to-first-voice, VAD tuning for research respondents, and provider quirks.

24 Feb 2026 · 11 min read

architecture

Production Voice AI for Research at Scale: The Architecture Nobody Warns You About (Part 1 of 8)

Part 1 of 6 — Why research interviews need server-side voice agents, the three-tier architecture, room metadata as configuration transport, and the 100-500ms propagation latency nobody tells you about.