Blog — Darko Trpevski

• GPT-Image 2.5: What Changed and When to Use It — GPT-Image 2.5 cuts latency in half, ships native inpainting, and is the first OpenAI model that makes automated product photography cost-viable at scale.
• Trying Out RAG Evaluation With RAGAS, Pinecone and Cohere — I wanted to see how RAG evaluation actually works, so I built a small tool-calling agent and scored it with RAGAS. The metrics were the easy part.
• Voice Assistants in Loud Places With OpenAI Realtime — 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.
• AI Construction Inspection Contractors Cannot Argue With — An AI construction inspection is only worth sending when each defect carries a clause reference and a named supervisor who verified it
• OpenRouter: Unified LLM API with Routing and Fallbacks — A unified proxy layer over multiple LLM providers with cost-optimised routing, fallback chains, and per-key security controls.
• Scaling RAG: Chunking, Reranking, and Cost Optimization — Ship RAG to production and watch it fail. Here's what works: semantic chunking, hybrid retrieval, reranking, and how to cut costs 5x.
• Multi-Agent Orchestration: Routing and Failure Recovery — Five agents talking to each other destroys context and costs money. Here's the pattern every major vendor converged on: one orchestrator, no loops.
• LangSmith Studio: Agent Evaluation and Monitoring — 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.
• N8N in Production: Lead Qualification That Works — N8N lead automation works for a week then breaks. Here's how to build it right: validation, fallbacks, locking, monitoring. 100% reliability.
• Which AI Model to Use: Claude, GPT-4, Gemini, or Self-Hosted — 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.