# The attention tax: what nobody tells you about 24/7 AI agents > Source: > Published: 2026-08-29 14:24:22+00:00 An agent that runs around the clock is sold as passive income. It isn't. It's a business that pays *you* nothing and bills *you* constantly — in the one currency you can't mint more of: **your attention**. We run such agents daily, and here are the three bills nobody itemizes — plus what legally reduces them. A tool that stays **connected** to your agent publishes its own definition in **every request**, whether or not that task uses it. Five servers left on is a toll collected five times per call. The fix is embarrassingly mechanical: prefer the tool that doesn't live in the context, and turn off what the task doesn't touch. A CLI called on demand costs nothing while idle; a connected server bills per request. We measured the same effect on a bigger scale with documents: reading a derived index instead of a raw vault made agent reading **~150× cheaper** ([the measurement](https://oroborolabs.github.io/posts/vault-index-150x.html)). Same principle, different layer: **what you keep loaded, you pay for on every turn.** An agent that notifies you of *everything* is training you to notice *nothing*. A notification that doesn't demand a decision is noise wearing a productivity costume. This one is qualitative — we have no counter for attention residue, and we won't invent a number. (House rule: a number without a method doesn't travel.) But the design fix is structural: **batch reporting**. One morning digest of what failed and what it cost beats a ping per event. The worst one, because it can't be automated away honestly. A 24/7 agent produces 24 hours of output; **reviewing it honestly also takes time**. Skip that budget and you haven't automated the work — you've relocated it to 2 a.m., where nobody audits it. Our answer is to make review *sampled and adversarial* instead of total and sleepy: a second agent whose explicit job is to **reject** the first one's work, with checks that produce a count — coverage (what's missing and why), depth (reopen a sample against the source), fidelity (sample the claims). Auditing a rejection attempt is far cheaper than vigilance. The punchline: **automating what you can't afford to audit isn't scale — it's debt, with interest collected in sleep.** *This is part of the working method behind a US$15 one-time template we sell — a second-brain vault starter that ships with an agent rules file, a derived index and search tools. Everything above works with nothing but a text file and discipline.* *Originally published on the Oroboro Labs site.*