# What can your agent reach? RiskMandate and the Agent Behaviour Policy, explained for the person who has to decide: what changed in v1.2.0, sgit.ai > The changes to the article "What can your agent reach? RiskMandate and the Agent Behaviour Policy, explained for the person who has to decide" in v1.2.0, paragraph by paragraph. *Source: · sgit.ai v0.7.87 · 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) / [What can your agent reach? RiskMandate and the Agent Behaviour Policy, explained for the person who has to decide](../../what-can-your-agent-reach.md) / [Versions](../what-can-your-agent-reach.md) / v1.2.0 # What can your agent reach? RiskMandate and the Agent Behaviour Policy, explained for the person who has to decide: what changed in v1.2.0 From v1.1.0 (2026-10-18, `de821285d`) to v1.2.0 (2026-10-18, `e9fbb78e9`), paragraph by paragraph. 0 paragraphs added, 0 removed, 2 changed in place, 51 unchanged. About 40 words added and 2 removed. Insertions are marked like this, deletions like this; unchanged runs are folded to one line; figures appear as their file names. [← v1.1.0](v1.1.0.md) · [all versions](../what-can-your-agent-reach.md) 32 unchanged paragraphs, under In short {#in-short}, The pages are hard to read {#pages}, What it is, in one paragraph {#what}… No, and that is deliberate. RiskMandate is "never in the request path": it reads what exists and models it, with "no runtime decisions, no enforcement point, nothing in line that can slow an agent down or break it." That is why a security review of it is a short conversation, and why it can describe agents it has no way of controlling, including commercial ones. riskmandate.ai's front page says "Enforced in real time, with alerts by text and email"; that is the enforcement the next paragraph describes, done by what sits in the path, not by RiskMandate itself, and the site's wording should say so. 3 unchanged paragraphs, under Beyond what it can reach: who decides {#decisions} To make it something you can see rather than read, we built the refund as a twin: [the Northstar refund twin](https://newsroom.sgit.ai/demos/vaults/northstar-twin/index.html), thirteen refund requests through four designs of the controls, every decision played and replayed. The design with a limit and good logs overpays $458 in a day; the design with three policies gets all thirteen right. [Allowed is not right](../../allowed-is-not-right.md) walks through it. It takes five minutes, and it is theafastestquick way I know to show someone that a control that works can still produce the wrong outcome. 16 unchanged paragraphs, under How does it get into the room? {#room}, What I would like to hear back {#back}, What this does not claim {#limits}… [← v1.1.0](v1.1.0.md) · [all versions](../what-can-your-agent-reach.md) --- *[Site index for agents](../../../llms.txt) · [HTML version](https://newsroom.sgit.ai/articles/versions/what-can-your-agent-reach/v1.2.0.html)*