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

Memberships

AI Automation Society

338.8k members • Free

Agency Service Scaling KingsšŸ‘‘

2.1k members • Free

EasyGrow 2.0ā„¢

591 members • Free

9 contributions to AI Automation Society
Free email warmup tool ideas?
Anyone got any free email warmup tool with a good reputation for google workspace?
0 likes • 5h
instantly.ai
Claude Code ai agent structure help
Trying to make my own personal EA and have a lot of stuff that I want to automate and communicate it through telegram but Im confused on how should I structure it. Should it be where I make one "God Agent" and that is where I prompt something like "give me analytics on ad spend from meta campaigns" or "review my most important emails" all in one AI Agent and pulls execution through a /tools folder... Or do I make separate Specialized AI Subagents Agents within claude code that have a command center within telegram and have a primary Agent that acts as a Chief of Staff and automatically triggers the appropriate agent for the task. What is the appropriate structure for the AI Engineers in here 😭 TY :)
0 likes • 6h
@Adrian Neely ok makes sense that one Orchestrator Agent is essentially the command center that I communicate with and Orchestrator Agent picks up the specialized agent to do said task BUT question I have is can these sub specialist agents communicate with one another so It doesn't loose context or is that the role of the Orchestrator Agent ?
0 likes • 5h
@Adrian Neely wouldn't that be more expensive ?
AI Operation systems
I have quite a few questions. Everyone is talking about AIOS as their own product and the possibility of a monthly retainer, but since you mainly focus on the power of Claude Code, I’m not really seeing how this is actually deployed to clients. Since Claude Code runs locally, you can do a one-time setup—folders, skills, config, context, etc.—and hand it over, but that’s where it ends. You don't have ongoing access to their local machine. On the other hand, if Claude Code is only meant for developing these systems, and the actual client solution is built from scratch using the Claude API, then it kind of loses me. The raw API doesn't have "skills," plugins, or commands out of the box—it honestly doesn't even come close to a polished tool like Claude Code. So, my main question is: What is your actual approach? How do you realistically build and deploy these AI systems in the way everyone describes? Thanks a lot! šŸ™
0 likes • 6h
you build everything on your own workspace then just give a ui to client
AIOS - building
Hey everyone, I've been looking into the idea of an AI operating system (as you see in the video below with Liam). I'm just wondering if any of you guys have put any thought to the process of actually building all your files around AI, on top of i.e. Claude Code inside of Visual Studio Code. If any of you guys are already doing it or are experimenting with it, how do you add a safety feature so Claude can't accidentally delete all of your files or your clients' files? Hope to hear from you šŸ™ https://www.youtube.com/watch?v=yd9tr0xqg-Y
0 likes • 6h
definitely something to keep eye on...
What One Day With AI Actually Looks Like šŸ”„šŸ”„šŸ”„
7 sessions. 11 commits. One Builder. One laptop. One AI partner. Total cost of AI tools used: £6.30. Not perfect. But learning and growing every day. SESSION 1: Content + Video Production - Published Sunday posts (Signal + Value Post) across all platforms - Generated 2 AI videos using Sora 2 (electrician at work, speed-to-lead phone notification) - Built a showcase heat map for social proof - Saved YouTube production checklist from academy feedback SESSION 2: Video Editing System - Locked in Remotion overlay positioning (lower thirds, key phrases, banners, captions with green word highlight) - Saved official CX logo, QR code, and shield logo - Built vertical (9:16) composition for YouTube Shorts and Instagram Reels SESSION 3: Video + Content Polish - Spliced hero video: talking head footage + AI-generated brand clip - Scaled all Remotion overlays for 720p - Built the vertical Short composition system from scratch - Published final Sunday content suite SESSION 4: Deep Research - DOAC AI Whistleblower - 6 parallel research agents analysed Steven Bartlett 3.4M-view AI Whistleblower episode (Karen Hao, 2 hours) - Fact-checked 59 claims against 50+ external sources - Produced 8 ready-to-publish daily posts (Mon-Thu next week) - 15 backlog content angles, 3 YouTube scripts, 5 Instagram carousel ideas - Branded Anthropic capability chart as social card SESSION 5: Systems + Meeting Prep - Audited 9 AIOS classrooms, produced gap analysis wiki page - Built Memory Health Scanner (weekly cron, Telegram alerts) - Built /memory-prune command for safe memory archival - Built /audit-website command (pre-Opportunity Map sales tool) - Built /space-review command (on-demand workspace health) - Built Competitor Monitor (weekly Firecrawl scrape + Claude diff) - Trimmed MEMORY.md from 513 to 87 lines - Prepped meeting pack for a prospect meeting on Tuesday - Archived 5 stale draft plans
What One Day With AI Actually Looks Like šŸ”„šŸ”„šŸ”„
2 likes • 4d
follow ups and speed to lead all done with GHL
1-9 of 9
@markos-pineda-7062
focus.

Active 11m ago
Joined Mar 2, 2026
INTJ
Powered by