Essays on shipping enterprise GenAI, AI-driven QA, RAG architecture, and production AI systems.https://semsudin.com/en-ushttps://semsudin.com/blog/seven-years-one-client/https://semsudin.com/blog/seven-years-one-client/The same client has kept hiring me across four different projects, from a Selenium migration to a multi-agent GenAI platform. I wrote down what I think drives that.Wed, 08 Apr 2026 00:00:00 GMTConsultingClient RelationshipsCareerhttps://semsudin.com/blog/cost-of-self-healing-qa/https://semsudin.com/blog/cost-of-self-healing-qa/I ran AI-driven self-healing on 1000+ tests for a global pet care company. This is what it cost and what it saved.Tue, 24 Mar 2026 00:00:00 GMTAI-Driven QATest AutomationEconomicsPlaywrighthttps://semsudin.com/blog/shipping-genai-reliably/https://semsudin.com/blog/shipping-genai-reliably/I architected a multi-agent platform at a global industrial company. This post covers why most enterprise AI never reaches production and what the projects that do reach it have in common.Tue, 10 Mar 2026 00:00:00 GMTAI SystemsGenAIArchitectureProductionhttps://semsudin.com/blog/image-promotion-not-direct-builds/https://semsudin.com/blog/image-promotion-not-direct-builds/Many CI/CD pipelines let production pull whatever the build server last produced. That is fine for a marketing site, but on an enterprise AI platform it leads to 2am rollbacks. This is the image promotion pattern I use on those platforms.Wed, 04 Mar 2026 00:00:00 GMTDevOpsCI/CDAI SystemsContainer Securityhttps://semsudin.com/blog/ai-agents-in-qa/https://semsudin.com/blog/ai-agents-in-qa/This post shows what it looks like when AI agents are integrated into the development cycle for test generation, self-healing tests and PR fixes. In most 'AI for QA' tools, the AI is bolted on.Sun, 22 Feb 2026 00:00:00 GMTAI-Driven QATest AutomationAI AgentsPlaywrighthttps://semsudin.com/blog/why-pgvector-over-pinecone/https://semsudin.com/blog/why-pgvector-over-pinecone/Enterprise RAG projects usually start by asking whether they need a dedicated vector database. On the enterprise GenAI platform I worked on, we chose pgvector. This is the decision framework I used.Tue, 10 Feb 2026 00:00:00 GMTRAGpgvectorArchitecture DecisionsAI Systemshttps://semsudin.com/blog/enterprise-rag-patterns/https://semsudin.com/blog/enterprise-rag-patterns/This is the decision tree I use when designing retrieval for enterprise AI. I start with vanilla pgvector and only add hybrid search or knowledge-graph traversal when the use case needs it.Sun, 18 Jan 2026 00:00:00 GMTRAGAI SystemspgvectorGraph-RAG