claim candidate goes to: this-edition T town planner

The agent behaviour policy is the due diligence document: a buyer reads the blast radius off it, and its absence says the most

A behaviour policy, written before an agent's first run, says what the agent is, which identity it uses, what it may read, write, not do and spend, who approves what, which risks were accepted by whom and for how long, and where its actions are recorded. Read by a buyer it says something else: the worst case (a deploy agent whose identity has no merge right and no production credential can at most break staging), which controls are enforced by the identity and which are only instructions, and which risks the vendor accepted on the buyer's behalf. A vendor with agents in its pipeline and no policy to show has agents whose blast radius nobody has written down, which is a finding before any code is read.

Decided by. Nobody yet: a candidate for Dinis to read, comment on and decide (keep, rewrite, merge, cut, article first, later, not doing it).

Note. Quote worth keeping: 'the moment of authorisation is not when you allow the agent to do something, it is the moment you give them the permissions.' A buyer reads the permissions, not the promises. Extends mandate-reach-gap from the operator's view to the buyer's.

Where it comes from

• Send an agent, not a spreadsheet The behaviour policy is the due diligence document (newsroom)

What it answers in the 2018 book

• Threat Modeling answered outline, Security

Where it goes

Chapter Controlling your agent: RiskMandate, part Build it without a server (drafting); topic Controlling your agent: mandate, reach and hope versus enforcement.

Other ideas proposed for the same chapter: Mandate, reach and the gap: hope versus enforcement, Code is a liability; the future is the smallest code that does the job, Learning to hack is still how you learn how things work: draw the line where the attacker is, The secret goes from the drop into the tool, never into the chat, Security experience is what lets you ship with known gaps: list them, match them to the reader, say what would change the call, A vault per conversation and per job: a leaked key exposes one small thing, not an inbox, The desktop is the barrier, not the model: prompt injection is not solved, so the box has to hold, Reach is a computed value, and new capability lands as excess, never as new authority, Who can pull the plug: an agent that cannot be stopped is riskier than one that can, A third input: a behaviour policy beside the system prompt and the prompt, which the vendor acknowledges, enforces where it can and answers for, Models do not separate code from data, so a rule in the prompt can be argued with by an email, Aviation and payments got safe when the rule, the liability and the business model pointed the same way, Zoom into an agent's behaviour policy and you find the business logic, which only the business can write, Software was the law: the rule the screen enforced by omission is no longer enforced once an agent calls the API, Every rule lands in one of three states: backed by a control, governed by an accepted risk, or resting on hope, Write down what your agent can reach in twenty minutes: list its tools, say what you wanted it for, write the gap.

Node idea:the-behaviour-policy-is-the-due-diligence-document in graph.json; see it in the graph. Source: admin/content/graph/ideas.json.