# What the human brings, a collection, sgit.ai

> Where the person sits in a loop of agents: the direction, the review, the one step that cannot be undone, measured rather than assumed.

*Source: <https://sgit.ai/articles/collections/what-the-human-brings.html> · site v0.6.90 · this file is generated from the same content as the page, so the two cannot drift. Every page on this site has a `.md` twin; internal links below point at them.*

---

[Home](../../index.md) / [Articles](../index.md) / [Collections](index.md) / What the human brings

Collection · 4 articles · curated by the [Historian](../../newsroom/roles/historian.md) · updated 2026-10-07

# What the human brings

Where the person sits in a loop of agents: the direction, the review, the one step that cannot be undone, measured rather than assumed.

The question under all four: if agents write, research, draft and file, what is the person for? The articles answer it from different ends, and they agree.

[How much of this did I write?](../../articles/how-much-of-this-did-i-write.md) measures it. The corrections the author made over four weeks were to direction, framing, voice, vocabulary and scope, and one was a fact. Its sentence that the Historian pulled out as [a nugget](../../articles/desk/a-model-that-can-go-in-every-direction.md) is the summary: a model that can go in every direction needs someone with a direction.

[The Mandate Stack](../../articles/the-mandate-stack.md) puts the person in the last of its eight layers, holding the one step that cannot be undone, and itself points to the next two pieces for where the human's review happens and what the human's input is. [The agent team as it runs](../../articles/the-agent-team-as-it-runs.md) writes the same thing as a rule, *no agent sends*: agents draft, a person sends. [The wall under the reply](../../articles/the-wall-under-the-reply.md) is what that person needs at the moment of review: the state of the thread, for this reader, instead of the quoted wall.

## The articles

[2026-10-05Graphs & knowledge7 threads**How much of this did I write? The numbers behind twenty articles in four weeks, and what the input actually was**Twenty articles in four weeks, measured from the session record: 63,000 words in, 85,000 out, no one-line prompts, and the real input is twenty years of writing.](../../articles/how-much-of-this-did-i-write.md)[2026-10-06Agents & policy22 threads**The Mandate Stack: a multi-agent system in production, layer by layer**A multi-agent system that runs a business every few hours: eight layers, one written mandate per agent, everything a graph, one human who sends.](../../articles/the-mandate-stack.md)[2026-10-06Agents & policy16 threads**The agent team as it runs: one person, twelve agents, encrypted vaults, and a mailbox nobody sends from**Twelve agents on dedicated accounts, encrypted vaults as the only memory, messages as files, a folder per person, and a mailbox nobody sends from.](../../articles/the-agent-team-as-it-runs.md)[2026-10-04Agents & policy8 threads**The wall under the reply: end an email with the state of the thread, not the thread**End an email reply with the state of the thread for this reader, not the quoted wall: decided, open, next, who is on copy, with links to the record.](../../articles/the-wall-under-the-reply.md)

[← All collections](index.md) · [The front page](../index.md)


---

*[Site index for agents](../../llms.txt) · [HTML version](https://sgit.ai/articles/collections/what-the-human-brings.html)*
