Reach is a computed value, and new capability lands as excess, never as new authority

What an agent can reach is not a document but the output of a calculation, so the question to answer is what calculates it and whether that is a one-time snapshot or wired to the pipeline. When a connector or integration is added the reach grows, the gap recomputes and a re-review follows; the mandate is locked business logic that changes only through change control, so a new capability can only land in the gap as excess, never as new authority. Unbounded includes volume: an agent permitted £10k per action that can perform a thousand actions carries a £10m exposure.

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. Status in the article: MVPs and proofs of concept, complete for simple single-agent deployments. The question's example is in dollars ($25k cap, $75k order) and the answer's in pounds (£10k mandate, £100k reach); the book should pick one currency.

Where it comes from

Ten hard questions for RiskMandate, answered 2. How do we keep behaviour policies current as agents gain new powers?; 1. What happens when an agent bypasses its behaviour policy? (newsroom)

What it answers in the 2018 book

Changes answered outline, Concepts
3rd-party-modules 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, The agent behaviour policy is the due diligence document: a buyer reads the blast radius off it, and its absence says the most, 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, 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:reach-is-a-computed-value in graph.json; see it in the graph. Source: admin/content/graph/ideas.json.