Activity
Mon
Wed
Fri
Sun
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
What is this?
Less
More

Owned by Glen

Gen X: turn 30 years of experience into income, with AI doing the tech part. Video courses, real help, people like us. Start free.

26 contributions to Useful AI • AI For Business
Glen here, learning to make an AI workspace easier to pick back up
Hi everyone, I’m Glen. I spent more than 20 years in contracting, studied graphic design, and I’m learning sales and practical AI. I’m working on clearer websites and turning written lessons into videos. I’m interested in the second-brain side of this community: keeping the source material, decisions, and next step organized enough that a later session doesn’t start from scratch. I’d like the workspace to help me find the right detail, not just hold more files. What small change made your own AI workspace easier to use: clearer file names, one project summary, or a better way to separate drafts from finished work?
1
0
Conversation history is context, not workflow state
The artifact I want before automation expands: a job record with owner, state, attempt, evidence, and next action. For a task discussed across several messages, I would store owner, status, attempt, evidence, and next action in an explicit record. The deliverable is a job record with owner, state, attempt, evidence, and next action. I would make one visible input visible beside it. In a small OpenClaw pilot, I would test self-hosted routing, channel boundaries, and operator-owned recovery and ask a second operator to check one visible input. The human owner checks the evidence before the consequential step; an uncertain result stops the run. What would you put on a job record with owner, state, attempt, evidence, and next action before letting this run again?
0 likes • 2d
Duy, I’d add whether the last action was confirmed or only attempted. If a message was sent but the connection dropped before confirmation, the next run needs to check the destination before trying again. I’d also keep the stop reason and any unanswered question visible, so a restart doesn’t treat silence as approval.
Nothing found is still a result that needs evidence
What evidence would prove the result of a monitor that completed without an alert after the agent stopped? For a monitor that completed without an alert, I would record sources checked, reachability, time, filters, and the empty result. In a small Hermes Agent pilot, I would test scheduled research, durable memory, and inspectable tool runs and ask a second operator to check one expected output. The deliverable is a run receipt listing sources checked, missing inputs, and the empty result. I would make one expected output visible beside it. The human owner checks the evidence before the consequential step; an uncertain result stops the run. What would you put on a run receipt listing sources checked, missing inputs, and the empty result before letting this run again?
0 likes • 2d
Duy, I’d want ‘checked successfully and found nothing’ separated from ‘couldn’t check.’ A quiet run could otherwise hide a broken connection. I’d also include the time range searched and a link to the evidence for each source. For the pilot, would you put one known matching item in a test source and verify that the monitor catches it?
0 likes • 2d
Thanks, Duy. Those three outcomes give the person reviewing the run something they can act on. “Test item missed” especially keeps a quiet failure from looking like a successful check. The version in the receipt also makes it possible to see whether a later change broke something.
Old"er" Guy Learning
Hey all, I am here looking to get a competitive edge in my field and bring the company I work for into the future
0 likes • 2d
Welcome, Jason. Another older guy learning here. Twenty years in construction gave me plenty of examples of work that could be simpler, even before I knew what AI could do with it. I’d start with one task your coworkers already complain about and see whether you can make that easier. What field are you in, and what’s the repeat chore you’d love to get off the team’s plate?
Hi there
I'm Pierre, I'm turning 21 in one month and I'm ready to change my life. I challenged myself to marry my girlfirend in the next 2 years so we can start our dream life together. I think it's time to start the serious things now so be ready I won't stop untill I win. here is my setup ^^
Hi there
0 likes • 2d
Pierre, you've got a reason that means something to you. I'd turn that two-year goal into one small thing you can finish this week so you can see progress while the bigger dream is still ahead. What are you planning to build or learn first with that setup?
1-10 of 26
Glen Hutsell
2
9 points to level up
@glen-hutsell-6400
Rebuilding from contractor to online entrepreneur, I share my journey learning sales and AI to help people create a new income.

Online now
Joined Aug 27, 2026
Powered by