Blog — StarDevsNotes from the StarDevs team on building AI agent systems, the infrastructure they run on, and measuring what actually got done.https://stardevs.gg/blog/2026-10-22T00:00:00ZTen Marks, One Hand: The StarDevs Diagram Kithttps://stardevs.gg/blog/diagram-kit/2026-10-22T00:00:00Z2026-10-22T00:00:00ZMykola LobanovThe glyphs we draw StarDevs systems with: the construction they share, the rules for putting them together, worked diagrams, and the files to do it yourself, under CC BY 4.0.The New AI Benchmark Is Cost per Completed Taskhttps://stardevs.gg/blog/cost-per-completed-task/2026-10-15T00:00:00Z2026-10-15T00:00:00ZMykola LobanovThe model benchmark tells you what a model can do. The production benchmark tells you what the system can finish, and at what cost: how to define, measure and report cost per completed task.The Production AI Agent Stack in 2026https://stardevs.gg/blog/production-ai-agent-stack-2026/2026-10-08T00:00:00Z2026-10-21T00:00:00ZMykola LobanovFrom model calls to governed systems that can plan, act, recover, and prove their work: the eight layers of a production AI agent stack, and how to tell a prototype from a system you can defend.Multimodal Agents Are Becoming Creative Teamshttps://stardevs.gg/blog/multimodal-agents-creative-teams/2026-10-01T00:00:00Z2026-10-01T00:00:00ZMykola LobanovVideo, voice, documents, slides, websites, and visual-to-code workflows are converging around a shared brief. The opportunity is to carry creative decisions through an entire project, and make the next revision easier.