IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

32 articles

27 Feb 2026 · 9 min read

audio-streaming

Next.js Integration: WebSocket & Audio Streaming for Azure Voice Live (Part 3 of 7)

Part 3 of 7 — The complete, production-ready code for integrating Azure Foundry Voice Live into a Next.js app. Full WebSocket proxy, useVoiceLive hook, audio capture and playback — every line explained.

27 Feb 2026 · 6 min read

azure

Project Setup & Azure Configuration for Voice Live (Part 2 of 7)

Part 2 of 7 — From zero to a working Azure Foundry Voice Live connection in under 30 minutes. Covers resource provisioning, region selection for minimum latency, authentication, and your Next.js project scaffold.

27 Feb 2026 · 9 min read

azure

Testing Voice Live & Transcript Analysis: Post-Interview Reports (Part 8 — Bonus)

Bonus Part 8 — Testing real-time voice AI is notoriously hard. Learn strategies for mocking, latency benchmarking, and LLM-as-judge evaluation. Then build a transcript analysis system that generates a scored interview report with specific action items.

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.

26 Feb 2026 · 14 min read

The Voice AI Interview Playbook: Video Interview Integration — Multimodal Analysis with Gemini Live (Part 8 of 12)

Part 8 of 12 — Adding video analysis to voice interviews with Gemini Live's multimodal capabilities. Frame sampling, parallel processing, screen sharing for coding interviews, and keeping costs under $0.40 per session.

25 Feb 2026 · 17 min read

livekit

The Voice AI Interview Playbook: Web and Mobile Clients — Building Cross-Platform Voice Experiences (Part 7 of 12)

Part 7 of 12 — From React to React Native to Flutter. Building cross-platform voice interview clients with LiveKit SDKs, audio visualization, and reconnection strategies.

24 Feb 2026 · 21 min read

The Voice AI Interview Playbook: Knowledge Base and RAG — Making Your Voice Agent an Expert (Part 6 of 12)

Part 6 of 12 — Your voice interviewer is only as good as what it knows. Here's how to build a real-time RAG system that retrieves rubrics, job descriptions, and technical knowledge in under 50ms.

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.

23 Feb 2026 · 28 min read

agents

The Voice AI Interview Playbook: Multi-Role Agents — Interviewer, Coach, and Evaluator Personas (Part 5 of 12)

Part 5 of 12 — Three personas, one infrastructure. How to build an AI interviewer that asks questions, a coach that gives feedback, and an evaluator that scores fairly — all with system prompts, function calling, and state machines.