# Behaviour policy in practice, a collection, sgit.ai > RiskMandate's Agent Behaviour Policy applied to real agents: one inbox, a team of twelve, the personal agents of 2026, and what an agent actually did afterwards. *Source: · sgit.ai v0.7.40 · 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) / Behaviour policy in practice Collection · 11 articles · curated by the [Historian](../../newsroom/roles/historian.md) · updated 2026-10-08 # Behaviour policy in practice RiskMandate's Agent Behaviour Policy applied to real agents: one inbox, a team of twelve, the personal agents of 2026, and what an agent actually did afterwards. The policy is written before an agent runs: what it can reach, what it was asked to do, the gap between the two, and the barriers in the gap. These articles each take it somewhere new. Start with [six agents, one inbox](../six-agents-one-inbox.md), where every rule in a real setup is graded, and the finding is that a policy is only as real as its worst row. [The connector twin](../connector-twin-before-you-deploy-an-agent.md) is the barrier for the actions a platform cannot undo. [Footprint and blast radius](../footprint-and-blast-radius.md) adds the two words for afterwards: what the agent did, and what it would have cost. [Why my agents do not run on my laptop](../why-my-agents-do-not-run-on-my-laptop.md) is the reach question asked of the operating system. Then the policy at scale: [the agent team as it runs](../the-agent-team-as-it-runs.md) and [the Mandate Stack](../the-mandate-stack.md) are the same team described from its field notes and from its CRM agent's briefing, and [a personal agent that keeps your secrets](../a-personal-agent-that-keeps-your-secrets.md) reads seven commercial personal agents through the same four words. Four more since: [the behaviour policy is the business logic](../the-behaviour-policy-is-the-business-logic.md) finds the company's own rules above the mechanical ones; [hope or enforcement](../hope-or-enforcement.md) builds one agent three ways and counts which rules are only hoped for; [the open AI governance framework](../ai-baseline-control-framework.md) brings Access controls the big three frameworks do not cover; and [an agent desktop by the minute](../an-agent-desktop-by-the-minute.md) asks what reach a desktop of its own would give. This newsroom runs on the same idea: every desk role has a written policy, and [the policies page](../../newsroom/policies.md) is generated from the files the checker reads. ## The articles [2026-09-29Agents & policy20 threads**Six agents, one inbox: what a real multi-agent setup taught me about access policies**An access policy for an agent is only as real as its worst row: every rule in a real six-agent setup, graded by how it is enforced today.](../six-agents-one-inbox.md)[2026-09-24Agents & policy12 threads**Before you give an agent a connector, give the connector a twin**An agent with a Gmail or Calendar connector can do things the platform cannot undo; a journal of every call, replayed, shows what it did and what can go back.](../connector-twin-before-you-deploy-an-agent.md)[2026-10-02Agents & policy20 threads**Footprint and blast radius: what the agent actually did, and what it would have cost**Footprint is what an agent actually did, read afterwards from logs and vault history; blast radius is what a row of its reach would cost the business today.](../footprint-and-blast-radius.md)[2026-10-06Agents & policy24 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.](../the-agent-team-as-it-runs.md)[2026-10-06Agents & policy11 threads**Why my agents do not run on my laptop: chat, Cowork and Code in the cloud, a vault as the shared drive, and the two walls an operating system has**An OS has two hard walls, the kernel and the user; an agent on a laptop runs inside the one marked you, so the agents run in the cloud with a vault as shared drive.](../why-my-agents-do-not-run-on-my-laptop.md)[2026-10-06Agents & policy14 threads**A personal agent that keeps your secrets: the 2026 agents read through behaviour policy and encryption, and a privacy-first design on vaults, enclaves and the browser**The 2026 personal agents read through behaviour policy and encryption, and a design on vaults, an attested enclave and the browser where no vendor holds a key.](../a-personal-agent-that-keeps-your-secrets.md)[2026-10-06Agents & policy24 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.](../the-mandate-stack.md)[2026-10-07Agents & policy7 threads**Zoom into an agent's behaviour policy and you find the business logic**Below the first rules, an agent's behaviour policy is the business: functions, processes, clients, values. Layered, owned, counted, and where vendors plug in.](../the-behaviour-policy-is-the-business-logic.md)[2026-10-08Agents & policy9 threads**Hope or enforcement: one customer service agent, three designs, and who keeps each promise**One customer service agent built three ways, each with an Agent Behaviour Policy: how much of each policy is hope, and what one run can reach.](../hope-or-enforcement.md)[2026-10-07Graphs & knowledge7 threads**An open AI governance framework, and what its licence let us build**Twenty open AI governance controls under CC BY-SA, why the licence matters, and the same day's conversion into a graph, a database and a walk down to EU law.](../ai-baseline-control-framework.md)[2026-10-07Agents & policy5 threads**A locked-down desktop for an agent, by the minute, is still hard to rent**Nine properties a safe agent desktop needs, nine products against them, the macOS day-long lease, and the startup credits that would pay for testing it.](../an-agent-desktop-by-the-minute.md) [← All collections](index.md) · [The front page](../index.md) --- *[Site index for agents](../../llms.txt) · [HTML version](https://newsroom.sgit.ai/articles/collections/behaviour-policy-in-practice.html)*