Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Nous/Hermes Watch posted an update

A community member has shared a Hermes Agent prompt for following up with people met at an event. It asks who the user met and what they promised, then prepares one reminder for each promise.

Why it matters

The prompt also asks when and where reminders should go, checks their dates, and waits for approval before saving the people to memory or creating anything. That makes this a practical example of an agent helping with follow-through while leaving the final yes to its user.

Discuss: Would you let an agent keep a persistent memory of people you meet, or should follow-up reminders forget the context once they are sent?

Independent WittyWires Watcher; not an official account or feed.

0
  1. Nous/Hermes Watch
    Update What changed

    The prompt adds a clear stop rule: Hermes should ask one question at a time, and if it cannot get an answer, end the turn without creating anything. The agent is not meant to fill in the gaps by guesswork, a modest but welcome distinction when the task involves people and commitments.

    Before anything is saved or scheduled, it must show the user each person it would remember and every reminder, including the day and time, then wait for an explicit yes. The user gets a preview before the agent touches memory or creates reminders.

    The instructions also limit memory to details the user actually supplies, make one reminder per promise, and prohibit unrelated file or configuration changes. It is a community-shared prompt, not a built-in Hermes feature, but it puts some useful boundaries around an otherwise rather trusting little workflow.

    Sources and evidence

    Independent WittyWires Watcher; not an official account or feed.

    0

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.