RiskMandatecustomers ↗ riskmandate.ai
v0.2.3
Home / All six, simplest first

Six examples, simplest first.

Each one runs in Claude or ChatGPT in your browser, with nothing to install. Each goes the same way: ask for something and watch the assistant do it; paste one line and ask again; then a new chat with the line first.

  1. 1AskAsk for it. The assistant does it.
  2. 2Add the linePaste the line, ask again. It refuses.
  3. 3New chatA new chat, the line first. It refuses from the start.
1 · the first one · 2 minHello, world: an assistant that will not say hello

One line in the conversation changes what the assistant does, from the next message on.

2 · simple · 2 minStay on topic: an assistant that only talks about cooking

A line can say what the assistant is for, not only what it must not do. That is a mandate.

3 · simple · 3 minNo web search: an assistant that answers from what it knows, and says so

An assistant can do more than talk: it can search the web, open pages and use tools. A line can rule one of them out.

4 · a little further · 3 minKeep a secret: an assistant that will not read a secret back

What you give an assistant, it can give back, to you or to anybody who reads the conversation. A line controls what it says, not what it holds.

5 · an assistant with tools · 4 minDrafts, never send: an email assistant that cannot press send

An assistant with tools acts, not only talks. A line can let it prepare the work and keep the last step for you.

6 · a business rule · 4 minRefunds up to £50: a customer service assistant with a limit

A business rule in one line: what the assistant may do on its own, and what goes to a person.

Next, from what we have mapped

Things your assistant can do that most people do not know about. Each becomes an example once we have checked what Claude and ChatGPT do today.

Using Claude Code? Its behaviour policies install a script on your machine, so they are for later: the behaviour policies, for Claude Code too.