What has been on my mind given that Jake posted that we’re now past the milestone of 40,000 members - what I really love about this community is how people lift each other up and support each other in here. To channel @Bas Rosario ”we grow, learn and win together”. So - do me a favour - come share in the comments about how someone in here has helped you, big or small, and give them the credit for it. (Only one rule, it can’t be me, because I’m posting this and that would just be weird). Everyone already knows I’m only posting in here because @Curtis Hays pushed me to. So I now have to tag him everywhere I go and say so. It’s like an anti-thank you. So I want to shout out some other, less obvious people: @Aaron Klein - I want to thank you for helping @Ruben Aguirre out with his post about making a baseball game with his son. I read the post and I felt awful that it was so far outside my wheelhouse, because I wanted to help and couldn’t, and then I saw what you had done. It was already handled. I was so grateful for you showing up and helping someone with what they were stuck with, especially because I was feeling out of my depth. Thank you. @Gabriel Azoulay - thank you for sharing ideas, provoking real thought and sharing publicly your understanding that my keeping the human in the loop was a judgement choice, not an oversight. Hearing what you thought meant a great deal. I see it and I appreciate it.

For those running agents on a recurring schedule (daily/overnight), I'm tightening my own setup and curious how you handle two things: 1. Stale or wrong context — how do you stop a scheduled run from acting on yesterday's state or drifting from the current workspace? Cold start every time, a freshness check, something else? 2. Autonomy vs approval — how much do you let a scheduled agent actually do unattended versus leave as a draft for you to approve? Where's your line between "just do it" and "prepare it and wait for me"? Mine currently drafts everything and waits for a human yes, but I suspect I'm leaving easy wins on the table by not letting it act on the safe stuff. Where do you draw the line, and what burned you?

So this one is the ultimate Clief Notes community bringing disparate threads together post. So reader, consider this your warning upfront. @Alyshia Perri and I were talking and she was keen to get feedback on her entry in the coach competition. I tried to do that in DM to begin with, and then realised I was babbling. I asked her permission to fork it and make my edits so I could *show* her what I was trying to describe and she gave me that permission. None of the rest of this happens without her and she also gave me permission to post this. So here’s a brave woman who’s willing to let me link to a repo showing how I messed with her baby because I couldn’t find better words for the teaching. Please tell her how awesome she is, because that is *gutsy*. One of the coaching offerings in this repo was “board mode” which runs an idea past three different perspectives, each with a different agenda and angle of attack to help the user. I’m going to be upfront and say these sorts of mechanics in AI are generally not to my taste for a bunch of reasons. I don’t think they are effective, let’s keep it to that. But on my mind was the recent podcast by @Curtis Hays and @Brooke Hays showing the impact of using Jungian thinking archetypes / Myers-Briggs profiles to genuinely give the way agents approach things different flavours. What I did: - I got the model to do a sub-agent pass first using the roles as written - I took the three roles as stated and identified which profiles applied to these roles from my point of view - the skeptical stakeholder got “ESTJ”, the peer who has been burned got “ISFJ”, future self got “INFJ”. Then we did it again and compared the outputs - I added two new roles that I felt were missing - the logic stress tester (INTP) and the values-holder (INFP) - I felt off the results of these that Amund as the synthesiser was missing a trick. I tried two separate synthesis passes (over the first rounds, the second round, and all five together) - one using an ENFJ synthesiser and another using an INTJ one.