User
Write something
Pinned
Sell AI Employees to Small Businesses (just steal mine)
I just built a full AI employee from scratch in this video. Everyone’s hyped on agents but barely anyone’s actually showing how to build ones that can really work inside a business. Here’s the entire stack I spun up live (no holding anything back): • Cloud computer running Hermes on Orgo • Its own email (AgentMail) • Its own phone number (AgentPhone + iMessage) • Telegram as the main chat interface • Every tool & connector hooked up through Composio • Credit card so it can actually spend money • Obsidian vault as its knowledge base / second brain • Latitude for observability so I know when shit breaks I made one main orchestrator agent (named it Hubert) that stays in charge 99% of the time and just hands tasks off to specialized sub-agents underneath it. One giant bloated agent is a nightmare to debug. This way everything stays clean and purpose-built. Full live build, every prompt I pasted, every terminal I opened… it’s all in there. And I’m giving away the complete templates for the orchestrator + every sub-agent I build going forward. I'm giving you actual employees that can do real work. Watch the whole thing here: PS - the template is free here on Github: https://github.com/nickvasilescu/nicks-stack
Field Note: AI-Ready Second Brain 4/8: Capturing and Reviewing Sources
In Part 3, I mapped the kinds of sources that can feed a Second Brain. That raised the next practical problem: How do I know what entered the system, what happened to it, and what still needs my attention? I’m working with two lightweight tools for this: a Second Brain Ingestion Log Lite and a Source Review Queue Lite. They sound similar, but they serve different purposes. The ingestion log is the receipt. It records meaningful captures and maintenance events, not every typo, wording change, or small edit. The goal is to preserve enough state to understand what happened and resume safely if the work stops halfway through. A useful log entry might answer: - What kind of source entered? - What action was taken? - Where did the resulting material go? - Is the work complete, partial, or blocked? - Where should I resume? This matters because a successful capture can still leave unfinished work. A source may have been saved but not synthesized. A note may have been updated while related material still needs checking. A maintenance pass may have started without reaching a safe conclusion. The log helps me avoid relying on memory to reconstruct that state later. The Source Review Queue Lite is different. It is not primarily about recording activity. It is a decision lane for captured material that may still require judgment. An item might need to be: - synthesized with related material; - merged into a canonical note; - adopted into the working knowledge base; - retained for reference only; - held for approval; - or intentionally ignored. That last option matters. An AI-ready Second Brain should not create an obligation to process everything. Some material will not be useful enough to justify more attention. The queue makes that an intentional decision rather than an accidental omission. The relationship between the two tools is simple: The log answers: What entered? What happened? Where do I resume? The queue answers: What deserves judgment? What should happen next?
0
0
Can Orgo Agents Communicate Directly?
Hey @Nick Vasilescu! I’ve been using Orgo for the past few days and have a question about something I believe you mentioned in one of your videos. You said agents can communicate directly with one another. Does Orgo have a built in feature that enables this? If so, how does it work?
Switch all your clients to these new AI Models
I said Grok 4.5 was a bigger deal than Fable Elon even liked my post but then GPT-5.6 Sol showed up So I gave 7 of this week's newest AI models their own computer and ran the same real tasks through Hermes Final ranking: 1. GPT-5.6 Sol: best overall 2. Grok 4.5: close second, fast and relentless 3. Muse Spark 1.1: the surprise of the week Benchmarks tell you what a model might do. Watching it control a computer shows you what it can actually do Full comparison ↓
1-30 of 117
Agent Empire
skool.com/agentempire
Learn how to build managed AI agents for your business or for clients using Orgo.
Leaderboard (30-day)
Powered by