Hey Academy, Join the AI Architects for support or to learn how to build your own agentic software. Most AI agents are a pain to set up—and that keeps people from actually using them. So I built an easier system you can use for free. In this video I’ll show you the Popebot in action by creating an email assistant that monitors my Gmail every 30 minutes, kills the spam, sends me Telegram DMs about urgent emails, and can even reply on my behalf. All built just by describing what I want. You’ll also see powerful features no other agent has: multi-user support with smart message routing, scoped agents that stay focused, seamless switching between chat mode and Claude Code CLI, voice-to-text, and a built-in scheduler. By the end, you’ll know exactly how to install it and start building agents to run your own life 24/7.

I run a UK digital agency and one of my clients is a builder who sends me raw build project videos via WhatsApp. We turn these into branded shorts and reels for YouTube, Instagram, Facebook, and Nextdoor. Current setup ($100/month): My VA in Nigeria handles the whole pipeline manually: • Downloads videos from WhatsApp • Runs them through Descript (adds voiceover when client’s ops manager hasn’t recorded one) • Polishes clips in Opus Clip Pro • Adds logo and branding • Writes captions • Schedules to YouTube, Insta, Facebook • Manually posts to Nextdoor via GHL workspace He’s reliable, the quality is OK, and at $100/month it’s hard to beat on cost. The AI-automated alternative I scoped: Make.com + Claude API + Creatomate (branding) + ElevenLabs (voice clone) + Opus Clip Pro API + GHL scheduling. Roughly £60-75/month in tooling, plus probably 20-30 hours of build time on my end. The build would handle: WhatsApp ingestion, Claude analysing each video and writing platform-specific captions, voiceover generation when needed, automated clipping, branding overlay, scheduled posting across all platforms, with one approval gate before publishing. Where I’m stuck: On paper the AI route looks cheaper long-term, but when I actually compare: 1. My VA costs $100/month flat, no build time, no API surprises, deals with edge cases naturally 2. The AI stack is ~£60/month in tools but needs my time to build and maintain, and breaks when APIs change or videos are unusual 3. Nextdoor still needs a human click either way (no API) 4. Voice cloning needs careful setup and consent 5. The VA can also handle other ad-hoc tasks the AI can’t My questions for the group: • Has anyone built something similar and found the maintenance cost was higher than expected? • Is there a hybrid worth considering — AI for the captions and Claude analysis, VA for the video editing and posting? • Am I overcomplicating this when a good VA with the right SOPs is genuinely the more cost-effective answer?

I currently have a manual podcast (audio only) process that I'm looking to automate and need some help to advise the easiest way to automate this: 1. Clean up Audio Recording (Top & Tail) - I use Adobe Audition currently 2. I then Run the audio through a AI filter to remove silences and ums and ahs 3. I transcribe the audio to create a file for this 4. I add the same intro & outro to the recording, this is faded in to the audio usually 5-6 seconds each end. 5. I generate a new Spotify podcasters episode 6. I upload a bespoke AI-generated image, placed on the background layer of a Canva File, I generate a catch Title for the episode (I have prompts) AI also generate the questions for a 1 1-month poll on the episode. 7. I also then generate social media posts (text + image) using ChatGPT and Claude and schedule to all channels each week. The process is pretty heavy so I'm looking at the best way to automate all of this, so it's easy as just uploading a raw MP3 with some basic information about the speaker and subject matter. Any help is appreciated. I'm familiar with Make.com and basic prompting using APIs.

So I just discovered the invideo.ai iOS app, typed a prompt about my business and it generated this in seconds. What do you think? Or should I stick to my $350 animated video here: https://youtu.be/93vVMAwHEW0?si=pX4Eg4GpjMBM-uY- Thoughts???

I've been experimenting with a faceless content generator that can use various inputs to generate a video (fully automated). With Images, narration, scenes, parts, captions etc. This is the very first version and test output but it's pretty cool. I spent most of the time building the structure of the system to be flexible and modular. So that you could have it produce other types of content -- simply by updating the interface vs having to reprogram a lot of automation for different use cases. Here was the article I used RIGHT HERE. And the video is attached to watch. How it works 👇 - Automation digested the article. - Created sources text. - Created the voice over narrative. - Created different scenes from the narrative and broke it into parts. - Then created images for each part. - Assembled it all back into a movie. - It created the voice narration. - Then added captions. No human was used to make any part of this video. Except the human who built it (me). ** note: one cool part of the system is that you can set it up so that each step could be moderated and adjusted before anything was generated. So if you wanted to, people could come in and augment any part of the video. Let me know what you think. Anything at all. Think its cool? Horrifying? Want something that can do something similar? Have other ideas? Let me know in the comments.