ZeroNonsense.dev ยท WritingEssays on Agentic AI from someone building the systems.https://zerononsense.dev/An AI agent shipped a working tool while I slept. Here's what I did and didn't let it dohttps://zerononsense.dev/writing/agent-shipped-while-i-slept/https://zerononsense.dev/writing/agent-shipped-while-i-slept/One person plus agents is a real operating model in 2026. The design question is not what the agent can do, but which verbs you refuse to delegate: push, merge, declare done.Thu, 09 Jul 2026 00:00:00 GMTYour AI context should not live in your AI vendorhttps://zerononsense.dev/writing/your-ai-context-should-not-live-in-your-ai-vendor/https://zerononsense.dev/writing/your-ai-context-should-not-live-in-your-ai-vendor/A portability stance, not a privacy one: keep your project's history, decisions, and state in three plain files you own, and any AI tool can pick up exactly where the last one left off.Sun, 05 Jul 2026 00:00:00 GMT98% of my AI token spend was overhead. Here are the 5 changes that cut ithttps://zerononsense.dev/writing/98-percent-token-spend-overhead-five-fixes/https://zerononsense.dev/writing/98-percent-token-spend-overhead-five-fixes/A practical follow-up: compacting, context trimming, handover files, and model routing to reduce token overhead in long agentic sessions.Thu, 25 Jun 2026 00:00:00 GMTI thought 80% of my token usage was re-sent contexthttps://zerononsense.dev/writing/the-actual-cost-of-mcp-tool-decoupling/https://zerononsense.dev/writing/the-actual-cost-of-mcp-tool-decoupling/In my agentic AI sessions, 85-98% of token spend was overhead. Here are the changes that actually reduced it.Thu, 18 Jun 2026 00:00:00 GMT