IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

21 articles

07 Aug 2026 · 5 min read

ai-agents

NVIDIA NOOA: When Your AI Agent Is Just a Python Class

NVIDIA's NOOA framework collapses the complexity of AI agent frameworks into a single Python class — methods are actions, fields are state, docstrings are prompts, type annotations are contracts. Here's what it means for teams building production agents.

20 Apr 2026 · 13 min read

Project Setup: BaseAgent, State, and Shared Infrastructure (Part 4 of 12)

Part 4 of 12 — Build the foundation: BaseAgent class, TeamState, agent config YAML, SQLite memory store, and tool registry.

18 Apr 2026 · 21 min read

Qwen Voice AI: Complete Guide to Building Interview Agents, Language Tutors & Voice Systems

Everything about Qwen's voice ecosystem — Qwen3-TTS, Qwen3-ASR, Qwen3-Omni, Qwen-Agent — and step-by-step implementation of Voice Interview Agent, Language Tutor, and Voice Tutor systems with full production code.

18 Apr 2026 · 21 min read

Qwen Voice AI: Complete Guide to Building Interview Agents, Language Tutors & Voice Systems

18 Apr 2026 · 19 min read

agentic-ai

Build an Agentic AI System From Scratch: Step-by-Step Implementation Guide

Complete hands-on guide to building a production-ready agentic AI system. From project setup to deployment — every layer implemented with working code, tests, and Docker compose.

31 Mar 2026 · 5 min read

The AI Toolchain War: Why Anthropic Bought Bun and OpenAI Bought Astral

Anthropic acquired Bun in December 2025. OpenAI acquired Astral (uv, Ruff) in March 2026. The AI model war has a new front: owning the developer toolchain. Here's what this arms race means for how you build software.

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.