Early-bird dates, speaker calls, and hotel blocks close on different days. The playbook will cover 30 payments conferences, picked from the 70+ PaymentsConferences.com tracks, so you can plan your 2027 budget in one place. Pre-order, $49 founding price: shanelogsdon.gumroad.com/l/p…
Today an agent bought domains with my credit card.
I approved it, then went back to my Saturday.
I set this up this morning as a productivity trial on xAI’s Premium plan: nine agents on Grok Bot, one orchestrator, and one Obsidian vault they all read from and write to.
Two things stood out on day one.
Side Hustle CEO is running a whole project on its own. My job is answering its questions and approving its decisions. One of those approvals was my first agent purchase: domains through Cloudflare, on the card I keep there. More on the project next week.
Drover is the one I’d build again first. Grok Bot handles the orchestration, and Drover hands the actual coding to the other agent subscriptions I already pay for (Claude Code, Codex, Pi and Cursor) running on a Mac mini.
Three of the nine came straight from the Grok Bot marketplace. You don’t have to build every agent yourself.
It’s day one. I’ll report back on what holds up after a week.
What’s the first decision you’d trust an agent with when your card is on file?
One subscription runs all of this: x.ai/pricing
Three of the nine came from the Grok Bot marketplace:
- dr eggbot by @poteto: x.ai/bot/marketplace/bots/dr…
- Copy Humanizer by Massimo De Luisa: x.ai/bot/marketplace/bots/hu…
- Side Hustle CEO by @AlexFinn: x.ai/bot/f5EvPVrHkyTX3piZyVm…
261 skills were sitting in my Pi configuration. 187,801 characters of names and descriptions, on every request, including the ones that needed none of it.
Beware if you try it. Skills Pi loads from directories you haven't listed leave your config and don't enter search. You have to tell it where to look.
Skills are with having. Paying for all of them on every request isn't.
MIT: github.com/slogsdon/pi-defer…
#AIAgents
Experimented with claude.ai pinned to my tablet home screen. Major win over the mobile app on the same device but doesn't auto refresh. Thoughts on making this supported use case @ClaudeDevs?
Finally wrote up the AI system I use to build my side projects in the cracks of a full life. Turned it into three free kits for building, marketing, and staying honest about follow-through. Public, MIT, free. You just need a paid Claude plan.
Want a few people to kick the tires before I share it wider. DM me. Story here: shane.logsdon.io/articles/st…
I thought what would crack under a full-time job and a family was the product. Wrong. The code holds up fine. The discipline around it doesn’t.
Forty minutes between a meeting and dinner is enough to write code, not enough to keep the habits that make it worth shipping.
A workflow that runs without errors can still be failing your core objectives through silent drift. You must measure the quality of intent, not just execution speed. shane.logsdon.io/articles/te…
A wrong workflow is harder to find than a broken one because it runs cleanly while the gap in quality accumulates. shane.logsdon.io/articles/te…
Adding an agent means writing a system prompt and pointing it at a model alias. Three ways to set it up: do it yourself, follow the guided setup, or run the Docker image.
github.com/slogsdon/hermes-d…
It runs on your hardware via Ollama + LiteLLM. In my case an M4 Mac Mini. Your phone reaches it over Tailscale, so the chat UI talks to your own machine and nothing leaves your network.


