Project Setup: BaseAgent, State, and Shared Infrastructure
Build the foundation: BaseAgent class, TeamState, agent config YAML, SQLite memory store, and tool registry.
#python
21 posts
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.
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.
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.
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.
Production Voice AI for Research at Scale: Deployment and Go-Live — From Docker Compose to 200 Concurrent Sessions
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.
Production Voice AI for Research at Scale: Multi-Language Voice AI — When Your Agent Needs to Think in Japanese
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.
Production Voice AI for Research at Scale: What Breaks at 200 Concurrent Sessions
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.
Production Voice AI for Research at Scale: The Real Cost
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.
Production Voice AI for Research at Scale: From Recording to Insight
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%.
Production Voice AI for Research at Scale: Multi-Phase State Machines
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().
Production Voice AI for Research at Scale: Zombie Agents, Pre-Warming, and the 5 Bugs That Cost Us Weeks
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.
Production Voice AI for Research at Scale: The Architecture Nobody Warns You About
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.
The Voice AI Interview Playbook: Multi-Role Agents — Interviewer, Coach, and Evaluator Personas
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.
The Voice AI Interview Playbook: Building the Voice Pipeline — STT, LLM, and TTS That Actually Work
Deepgram Nova-3 or Whisper for STT? Gemini Flash or GPT-4o for conversation? ElevenLabs or Cartesia for TTS? Real benchmarks, real costs, and the combinations that actually work in production.
The Voice AI Interview Playbook: LiveKit vs. Pipecat vs. Direct — Picking Your Framework
LiveKit gives you WebRTC infrastructure. Pipecat gives you pipeline flexibility. Direct integration gives you simplicity. Here's how to choose for your voice interview platform.
Building a Production Voice AI Interview Agent: S2S-Only with Dynamic Prompts
A practical build guide for a speech-to-speech interview agent using LiveKit MultimodalAgent, OpenAI Realtime, and Gemini Live. Dynamic system prompts, 3 personas, function calling, and provider switching — no cascaded pipeline needed.
Building an AI Voice Interview Platform: What Actually Worked (and What Didn't)
Lessons from building a real-time AI interviewer with LiveKit, OpenAI Realtime, Gemini Live, and Bedrock Nova. VAD tuning, provider failover, latency budgets, and the things nobody warns you about.
I Spent a Weekend Building AI Agents. Most of Them Were Useless.
I experimented with CrewAI and LangGraph to build multi-agent workflows. Some were genuinely useful, some were expensive toys. Here's what I learned.
Our First RAG System Was Terrible (Here's What We Fixed)
We built a RAG knowledge base. The first version gave wrong answers half the time. Six months of iteration later, it actually works. Here's every lesson.
I Tried Five Vector Databases. Here's What I'd Actually Use.
We tested ChromaDB, Pinecone, Weaviate, Qdrant, and pgvector for our RAG system. Benchmarks, costs, developer experience — and the one I'd pick today.
Stay in the loop
Get notified when I publish new posts on AI, .NET, cloud architecture and more.