https://trpevski.com SaaS founder and AI engineer. Two products in production — writing about the decisions that only look obvious afterwards. en-us Sat, 29 Aug 2026 20:30:50 GMT https://trpevski.com/blog/voice-assistant-noisy-environments-openai-realtime https://trpevski.com/blog/voice-assistant-noisy-environments-openai-realtime Sun, 30 Aug 2026 00:00:00 GMT One OpenAI Realtime voice component fills every form in a restaurant app, survives a loud room, and gets almost all of its tuning through the prompt. https://trpevski.com/blog/ai-construction-inspection-contractors-cannot-argue-with https://trpevski.com/blog/ai-construction-inspection-contractors-cannot-argue-with Wed, 26 Aug 2026 00:00:00 GMT An AI construction inspection is only worth sending when each defect carries a clause reference and a named supervisor who verified it https://trpevski.com/blog/langsmith-studio-agent-evaluation-and-monitoring https://trpevski.com/blog/langsmith-studio-agent-evaluation-and-monitoring Mon, 10 Aug 2026 00:00:00 GMT Ship LLM agents blind and you'll lose money. LangSmith Studio gives you visibility into what your agent actually does, catches problems before users do. https://trpevski.com/blog/scaling-rag-chunking-reranking-and-cost-optimization https://trpevski.com/blog/scaling-rag-chunking-reranking-and-cost-optimization Mon, 10 Aug 2026 00:00:00 GMT Ship RAG to production and watch it fail. Here's what works: semantic chunking, hybrid retrieval, reranking, and how to cut costs 5x. https://trpevski.com/blog/multi-agent-orchestration-routing-and-failure-recovery https://trpevski.com/blog/multi-agent-orchestration-routing-and-failure-recovery Mon, 10 Aug 2026 00:00:00 GMT Five agents talking to each other destroys context and costs money. Here's the pattern every major vendor converged on: one orchestrator, no loops. https://trpevski.com/blog/n8n-in-production-lead-qualification-that-works https://trpevski.com/blog/n8n-in-production-lead-qualification-that-works Mon, 10 Aug 2026 00:00:00 GMT N8N lead automation works for a week then breaks. Here's how to build it right: validation, fallbacks, locking, monitoring. 100% reliability. https://trpevski.com/blog/openrouter-unified-llm-api-with-routing-and-fallbacks https://trpevski.com/blog/openrouter-unified-llm-api-with-routing-and-fallbacks Mon, 10 Aug 2026 00:00:00 GMT A unified proxy layer over multiple LLM providers with cost-optimised routing, fallback chains, and per-key security controls. https://trpevski.com/blog/which-ai-model-to-use-claude-gpt4-gemini-guide https://trpevski.com/blog/which-ai-model-to-use-claude-gpt4-gemini-guide Sat, 01 Aug 2026 00:00:00 GMT Choose the right AI model for your use case — when to use Claude, GPT-4, Gemini, Qwen, or self-hosted based on speed, cost, and privacy.