https://kodexlabs.dev/blog Essays on building AI systems, shipping product, and the infrastructure behind them, from the Kodex team. en-us https://kodexlabs.dev/blog/how-to-vet-a-development-agency https://kodexlabs.dev/blog/how-to-vet-a-development-agency Polished answers are cheap. When you vet a development agency, the useful signal is not whether they have answers. It is whether their answers have edges. Sun, 01 Nov 2026 00:00:00 GMT Delivery https://kodexlabs.dev/blog/ai-agents-in-production https://kodexlabs.dev/blog/ai-agents-in-production Every demo works on a clean input. Production runs on mess — missing context, adversarial users, and the long tail of edge cases. This is what it actually takes to put an agent on real traffic and keep it there. Tue, 14 Jul 2026 00:00:00 GMT AI Systems https://kodexlabs.dev/blog/rag-that-answers https://kodexlabs.dev/blog/rag-that-answers Your model isn't the bottleneck. Your retrieval is. Most RAG systems fail because the data layer was designed for search, not for answers. Here's the pipeline that holds up. Sun, 28 Jun 2026 00:00:00 GMT AI Systems https://kodexlabs.dev/blog/llm-security https://kodexlabs.dev/blog/llm-security Prompt injection gets the headlines. It's also the least of it. The real risk in an LLM system is agency — the tools you gave the model — and the data it can reach. Here's the threat model we actually use. Wed, 10 Jun 2026 00:00:00 GMT Security https://kodexlabs.dev/blog/platform-engineering https://kodexlabs.dev/blog/platform-engineering Internal platforms fail when they're built for the engineering team instead of for the business. The ones that earn their budget solve one problem: how fast a product engineer goes from day one to 'it's in production'. Fri, 22 May 2026 00:00:00 GMT Platform https://kodexlabs.dev/blog/shipping-without-compromise https://kodexlabs.dev/blog/shipping-without-compromise 'We had to cut corners to ship' is a story we hear constantly. It's also usually false — the corners got cut long before the deadline, in the scope, in the reviews, in the definition of done. Here's the delivery discipline that avoids it. Fri, 08 May 2026 00:00:00 GMT Product https://kodexlabs.dev/blog/observability-for-ai https://kodexlabs.dev/blog/observability-for-ai Your error rate says nothing about whether your LLM product is getting better. Quality in an LLM system is a moving target, and most dashboards can't see it. Here's what to log, trace, and alert on. Fri, 24 Apr 2026 00:00:00 GMT Reliability