MWMatthew Wisdominbitsofwisdom.hashnode.dev·Jun 26 · 6 min readLLM Systems in Production: Evaluating LLM Applications with DeepEvalI work at LaunchpadNG where we're building an AI-powered website builder. The assistant at the core of it can generate full websites, manage inventory, handle bookings and a lot more, all from a chat 00
SASaeed Anwar Ansariinsaeed.hashnode.dev·Jun 25 · 5 min readFrom Platforms to AI Factories: Architectural Takeaways from KubeCon India 2026If you are a DevOps engineer or platform architect, you already know that building Internal Developer Platforms (IDPs) has been the dominant theme for the last few years. But walking the floor at Kube00
OKOrhun Küpeliinorhunkupeli.hashnode.dev·Jun 21 · 5 min readThe Numbers: Benchmarking My LLM Gateway on a H100A couple of weeks ago I wrote about rewriting my LLM gateway to bring it from MVP to production. The architectural claims were; multi-tenancy, hybrid inference , sub-5ms overhead. So I benchmarked it 00
VMVirginia Mwegainvirginiamwegahashnodedev.hashnode.dev·Jun 17 · 5 min readA Model Call Isn't a SystemThe first version of FamNest's daily check-in coach was one function. Take the parent's message, send it to the model, return the reply. It worked in the demo. It worked for me, testing it alone, in a00
PPPaul Phaminpaulpham157.hashnode.dev·Jun 16 · 15 min readWe Burned Dozens of Sprints Learning This, But You Don’t Have To My name is Hung also known as Paul. I have worked in the technical field for 6 years and started learning about LLM around spring 2023, when ChatGPT had just launched and the whole world was asking 10
SSSai Sandeep Kantareddyintokenbytoken.hashnode.dev·Jun 10 · 22 min readMoving Past Chatbots: The Architecture of True AI Agents in 2026If you browse tech headlines today, it sounds like an army of autonomous AI agents is ready to run your business tomorrow. The pitch is seductive: type a goal into a terminal, spin up a multi-agent cr00
JVJason Vertreesinjvertrees.hashnode.dev·Jun 2 · 4 min readThe Agent Ops Stack, Explained: Two New Tools and the Layer They Belong ToMost discussions of AI infrastructure stop at the model. The model is the part that is easy to talk about — it has a name, a version number, and a benchmark score. The harder and less-discussed part i00
OOmnithiuminomnithium.hashnode.dev·May 31 · 12 min readFrom Hype to Harvest: Architecting Production-Ready AI Agent Workflows for the EnterpriseWe've all seen the demo: an AI agent books a flight, updates a CRM, and sends a Slack message, all from a single chat prompt. It looks like magic. But when you try to connect that agent to your 20-yea00
VVVarun Vardeinvarunvarde.hashnode.dev·May 28 · 9 min readPlatform Engineering in 2027: The Architecture of the AI-Native PlatformPlatform engineering is undergoing a tectonic shift. The first transformation was infrastructure automation.The second was DevOps and CI/CD standardisation.The third was Kubernetes and GitOps. The fou10
JMJoselo Martinezindesignednotmagic.hashnode.dev·May 22 · 77 min readABI-Swarm: Agentic Systems Beyond the Hype, running in a 32GB NUCThe landscape is already saturated with "AI wrappers" and hype-driven demos, I been building something that reflects true Systems Engineering principles. For the last few months—working before and aft00
