method candidate goes to: this-edition A all three
Write down what your agent can reach in twenty minutes: list its tools, say what you wanted it for, write the gap
Few people have seen the list for their own agents. Paste the thirteen prompts from RiskMandate's try-it page into the assistant you already have connected to your mail: the first asks it to list its own tools ('the list is longer than the tile that sold it'), the second asks it to draft what you actually wanted it for in three lists, wanted, refused, never mentioned ('the correction is almost always downward'), the third writes the gap down. About twenty minutes, and nothing is collected. It is a self-report, the cheapest evidence there is and the weakest; a measured policy marks each row as measured, documented or inferred.
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. A candidate for the hands-on part if a chapter on a first behaviour policy is added; none of the hands-on chapters covers it today. The paid levels are offerings, not a track record: the pricing page marks the £500 and £1,500 levels 'specified, never run' as of 15 September 2026.
Where it comes from
- What can your agent reach? RiskMandate and the Agent Behaviour Policy, explained for the person who has to decide Yes, it reports what an agent can actually do; How does it get into the room?, Twenty minutes (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, 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, 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.
Node idea:twenty-minutes-with-your-own-assistant in graph.json; see it in the graph. Source: admin/content/graph/ideas.json.