surehand
Articles / Reference / Page 3

The reference for governing AI agents, one question at a time., page 3

One question, answered in full, for the people who have to sign off on an agent.

posts
31
updated
feed
rss
Regulation

SOC 2 when the product is an agent: what the report covers, and what it does not

Reference5 min read

A SOC 2 report tells you a vendor's controls over your data were designed and, in Type 2, operated. It does not tell you what their agent will do on your work. How to read one.

Meta

The stack for governed agents: six layers between a model and your ledger

Reference6 min read

A map of what sits between a language model and the system it changes: model, orchestration, tools, control, record, and the system of record itself.

Controls

The two-person rule for AI agents: overrides, dual authorisation, and Meta's Rule of Two

Reference6 min read

Two people to override a block. Where the rule comes from, what it should cover for an agent, and why Meta's 'Agents Rule of Two' is a different rule with a confusing name.

Governance

What is an agent approval policy?

Reference5 min read

An approval policy decides which agent actions go ahead, which wait for a person, and which never happen. Most teams have a paragraph. You need a table.

Controls

What is an agent control plane?

Reference6 min read

An agent control plane checks every action an AI agent wants to take against your rules before it runs, holds the hard ones for a named person, and records the result.

Controls

What is an agent permission manifest?

Reference6 min read

A permission manifest is the signed list of what an AI agent may touch, spend and decide alone. Anything not on the list is refused. What one contains, and why a prompt is not one.

The product

The controls in these notes are what Gatehouse, Surehand’s control plane, enforces at runtime.

See Gatehouse
[ your next step ]

Bring us the queue nobody wants.

One process, studied in writing. You keep the document, whatever it says.

support@surehand.io