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

Owned by Nick

Build, run, and sell managed AI agents for your business or for clients. A free community founded by Nick Vasilescu.

Skool Course
36.7k
$29/m
Skoolers
152.5k
Free
49 contributions to Agent Empire
What will your agent finish tonight? New episode with Karsten Stinis
The new Agent Operators episode with Karsten Stinis is live. Karsten installs managed AI agents for businesses in Belgium. His offer is €2,750 for the setup, then €250 a month for support. The part I'd pay attention to is what happens during the installation: he watches the client work, finds a recurring task, and aims to have something useful waiting for them the next morning. Before you install the agent, decide what it will finish. A morning briefing is a good example: meetings, open tasks, and unanswered emails worth following up on. The person can open it, check the sources, and decide whether it helps. Whether you're building for yourself or a client, try scoping one overnight job: 1. The job: choose one recurring task. 2. The inputs: name the inbox, calendar, or task list it needs. Connect the accounts and check access. 3. The result: decide where the output should appear and when it should be ready. Make it easy to trace back to its sources. 4. The review: choose who checks it. Keep outgoing messages as drafts for the first run, and have a person approve them. Run it once. Read the output with the person who will use it. Use their corrections to improve the next run before adding another job. In the episode, Karsten walks through Hermes on Orgo, Composio for connecting business tools, Honcho for memory, and how he monitors usage and incidents. Keeping the workflow working is part of the service. He also reports one client's agent setup being built in 22 minutes. Humans still handle the tool and account connections. Watch the full conversation: How He Sells AI Agents for €2,750 + Monthly Support https://www.youtube.com/watch?v=Y8MJG3iDtSo What would you want your agent to have ready tomorrow morning? Share the job below.
1 like • 6d
appreciate it mahin glad these are cutting through the noise for u. more coming
0 likes • 60m
@Harsha Edpuganti great qs harsha 1. different market. karsten sells to local smbs in belgium who mostly have no idea what an agent is yet, so a lower install plus a small monthly retainer gets him in the door and it compounds. same playbook, different price point 2. honestly nothing, and that's fine. his clients start building their own dashboards after about a month. the retainer pays for keeping it running: monitoring, fixing what breaks, shipping upgrades. most owners don't want to be the one doing that 3. yes, still working on it. for now the pinned videos are the path, start here https://www.youtube.com/watch?v=fAhwYrjmQRk
Episode 3: Stop being the copy-paste layer between your AI agents
Most multi-agent demos stop at "look, two agents can talk." In a client business, the hard part is knowing who owns the work, whether it was actually done, and what happens when an agent stalls. For Episode 3 of Agent Operators, I sat down with Jason Myers of AppLayer. He built Tango after realizing he had become the human copy-paste layer between his agents. We connected Hermes to a shared task list, watched workers claim jobs, and dug into audit trails, task leases, and recovery. Then I showed how Orgo cloud computers let you see and control the work when an agent needs a real desktop. In the conversation: • 04:19 — Hermes creates a task in Tango • 19:56 — Preventing two agents from doing the same job • 21:16 — Recovering stalled tasks • 30:25 — Agents working on Orgo cloud computers Watch the full 36-minute episode: https://youtu.be/LKCZXIGmrY4 If you’re deploying agents for clients, where do your handoffs still depend on you?
0 likes • 7h
good q jordan if you're solo and running one or two agents on your own laptop, you probably don't need orgo yet. keep the sprawl small where it starts to matter is when an agent has to keep running with your laptop closed, or you're setting one up for a client. then it needs its own computer with its skills, tools and state living on it (for hermes that's ~/.hermes/), and orgo is that computer nous mcp or the claude code sdk is the brain, orgo is the box it runs on, so they stack https://docs.orgo.ai/guides/hermes
The Demo to Delivery Drop-Off
Getting an agent to complete a workflow on your own machine feels like magic the first time it works. But taking that working test script and actually packaging it into a reliable service a client can use daily is where things get messy. You go from debugging logic to chasing edge cases, handling output checks, and trying to keep client communications organized. For those building managed agents here, where does the real friction start once the core workflow actually runs?
1 like • 5d
Yep this is the gap. A demo that runs on your laptop isn't the product. Friction starts when the run has to keep working when you are not watching: edge cases, checking the output, and what the client hears when something breaks. nice work naming it and on receipt vs follow-up: if the run can close itself with evidence, it stays a receipt. If a human has to approve, decide, or supply missing input, it becomes a follow-up. https://docs.orgo.ai/guides/hermes
Help me Nick ! !
Hey @Nick Vasilescu I've a question for you , the question is that : 1. what's the best way to get my first client cold calling or cold email ? Give a solution pls I'm suffering to get client . What should I do to get my ever client ? please help me bro .
1 like • 5d
hey mahin, thanks for asking this straight cold call vs cold email is the wrong first fork. steal the offer first: one clear AI employee you can sell to a small business, then pick whichever channel you can actually stick to for ~20 real conversations. this is the playbook (also pinned here): https://www.youtube.com/watch?v=fAhwYrjmQRk
If you vibe code client projects, this is the backend problem nobody talks about.
The front end is easy. Lovable, Claude, Cursor — done in hours. But the moment a client needs real pricing logic, business rules, or calculations — you're either hard-coding it into prompts or writing custom backend code. Both are a nightmare to maintain when something changes. I built a solution. Here's how it works: → You vibe code the front end (any tool) → It connects to n8n → n8n pulls the business logic from Quotix (the engine I built) → Quote calculated, result returned to the front end → Lead pushed to GoHighLevel automatically No black box. No hard-coded prices. Full control over the business logic from one place. https://www.loom.com/share/256a189b6ba74aa2bf53aeab14569bc0 I'm looking for people to test this. If you build for solar, HVAC, roofing, electrical — or any service business that needs on-site quoting — drop a comment or DM me. Free to test.
If you vibe code client projects, this is the backend problem nobody talks about.
2 likes • 9d
@Hisham Juneidi appreciate the ask hisham on the orgo side we put business logic on the agent computer, not only in chat and not only in the workflow graph. hermes skills + tools, files, and an ICM-style home a fresh agent can open: what it can do, what ran last, what still needs you. that durable home is the product; the computer is where it lives. https://docs.orgo.ai/guides/hermes
0 likes • 9d
appreciate the ask hisham orgo is the computer the agent lives on. with hermes, skills + tools + state in ~/.hermes/ stay on that box across sessions, not just in the chat or the n8n graph https://docs.orgo.ai/guides/hermes
1-10 of 49
Nick Vasilescu
5
26 points to level up
@nick-vasilescu-7920
building computer use agents

Active 5m ago
Joined Nov 19, 2025
Powered by