With July 7th coming up, I’ve been thinking less about using Fable and more about capturing its value. My approach has been to spend my remaining time with Fable on work that only Fable can realistically do. Not writing code. Not debugging. Not implementing features. Instead, I’ve been asking it to design systems, challenge architectures, and produce implementation specifications for projects that are simply too large or too interconnected for me to have tackled with previous models. The key is this: The output isn’t the final product. The output is a specification detailed enough that Opus, GPT-5.5, Codex, or another implementation model can execute it later. In other words, I’m using Fable to build my implementation backlog. By the time July 7 arrives, I don’t want to have “used” Fable for a few conversations. I want to have months of high-quality architectural work waiting to be implemented. It’s almost like borrowing the brain of a senior architect for a limited time, then leaving the office with a stack of blueprints your engineering team can build from over the coming months. If you still have access, I’d encourage you to spend less time asking it to do the work and more time asking it to define the work. That knowledge doesn’t disappear when access ends. In many cases, it’s the most durable asset you’ll get from the entire preview.

If you're still letting the same AI model write and review your code, you're missing half the bugs. Last week Scott dropped the adversarial review playbook (spoiler: make Claude and Codex argue), Juan proved photo booths are back—but make them AI. Miss it and you missed the memo on actually shipping. 📞 HOW THE CALLS WORK The calls can run 2+ hours. We want to make sure we're respecting everyone's time. Especially those of you who actually show up. Here's the structure: 👉 Reply to this post with your questions before the call 👉 If you submit a question and you're on the call, you go first 👉 We work through questions in the order they came in 👉 Then we open it up for everyone else If you can't make the call but want your question answered, drop it in the comments. We'll get to it. But priority goes to people who are there. The goal is simple: if you're taking the time to show up, you shouldn't have to wait behind questions from people who aren't even on the call. Bastian should be open-sourcing that Pixir harness any day now, and I'm curious whether Scott and Patrick have started plumbing those security review hooks into Hermes. Plus, Ty's got his Limitless recovery and voice coding demos ready to roll. Want first dibs on these threads? Drop your questions early. 🔗 ZOOM LINK (save this) https://us06web.zoom.us/j/81995207847?pwd=Xe6u6LmIQOmCP5VTnOwWYjDBfZNKGB.1 📅 WHEN Tuesday July 7th at 6PM ET Looking forward to seeing you on the call!

AI Developer Accelerator — Coaching Call - June 30 VIEW RECORDING - 148 mins (No highlights) Meeting Purpose Members share AI project updates and discuss business strategies. Key Takeaways - New Business Models: AI enables new models for monetizing underutilized assets (e.g., parking lots, event venues) and data ownership (Payback Owned). - AI-Native Dev Workflows: Members are building advanced AI systems for development, including voice-controlled coding agents (Ty), automated home lab management (Agent Ops), and multi-model code review pipelines (Scott). - Strategic Cold Outreach: Brandon's high-value, personalized Loom videos are booking demos by articulating customer problems better than they can, proving effective for his EMS app. - Scaling Hardware-Software: Juan's AI photo booth is a platform for high-margin event rentals. The proposed strategy is to prove the model, then scale via a "vending machine" franchise or a revenue-share partnership with venues. Topics Business & Go-to-Market Strategy - Brandon's EMS App: - Gaining traction with a HIPAA-compliant v2. - Pipeline exceeds $100k from a conference booth. - Cold outreach strategy:

📝 SUMMARY This week's show-and-tell call featured deep dives into production AI implementations across software development, business operations, and hardware ventures. Brandon Hancock shared progress on his EMS startup including a $100K sales pipeline and personalized cold outreach systems, while demonstrating new Even Realities smart glasses with Claude Code integration. Patrick Chouinard unveiled AgentOps, a comprehensive homelab automation harness using Hermes, NATS, and multi-model PR review loops. Scott Rippey presented adversarial security review hooks using Claude and Codex, Ty Wells showcased creative problem-solving by recovering a lost wearable via GPS cross-referencing and voice-driven coding agents, Juan Torres demoed an AI photo booth hardware venture with franchise potential, and Bastian Venegas Arevalo introduced Pixir, an Elixir-based agentic framework optimized for memory efficiency. The session centered on practical strategies for revenue generation, automated code review pipelines, and building defensible businesses at the intersection of physical hardware and AI. 💡 KEY INSIGHTS Cold Outreach Feedback Loops: Send personalized Loom videos to prospects, then extract exact language from discovery calls to refine your next pitch deck. Over time you articulate their problems better than they can, dramatically improving conversion. Sniper vs Spray Outreach: With finite addressable markets like 18,000 EMS agencies, high-value hyper-personalized outreach beats mass email blasting. Burning the market with low-quality touches is irreversible. The Reviewer Bottleneck: When AI accelerates code production 10x, human review becomes the bottleneck. Solve this with sandboxed ephemeral environments like Supabase branches and parallel feature development. Work Backwards from Revenue: Calculate exactly how many daily outreaches are needed to hit target revenue within a defined timeframe. This converts abstract goals into simple daily checklists and removes timeline anxiety.

**THIS IS A BRANDON WEEK, don't miss him** Last week we watched an entire video production pipeline run itself end-to-end while Claude somehow compressed two months of estate paperwork into a single weekend. If you've ever wanted to talk to your codebase like it's a senior dev over coffee—or just automate the boring stuff so you can focus on the fun stuff—this is the week to jump back in. 📞 HOW THE CALLS WORK The calls can run 2+ hours. We want to make sure we're respecting everyone's time. Especially those of you who actually show up. Here's the structure: 👉 Reply to this post with your questions before the call 👉 If you submit a question and you're on the call, you go first 👉 We work through questions in the order they came in 👉 Then we open it up for everyone else If you can't make the call but want your question answered, drop it in the comments. We'll get to it. But priority goes to people who are there. The goal is simple: if you're taking the time to show up, you shouldn't have to wait behind questions from people who aren't even on the call. Scott is bringing back that fully automated video pipeline for a larger demo plus a new voice-based codebase conversation tool, while Ty continues building out his CodeTalk voice interface on Proxmox. Morgan is also stress-testing AirLLM to see if consumer hardware can really handle 32B+ models—if you've been curious about local inference without the enterprise price tag, come see how the experiment turns out. 🔗 ZOOM LINK (save this) https://us06web.zoom.us/j/81995207847?pwd=Xe6u6LmIQOmCP5VTnOwWYjDBfZNKGB.1 📅 WHEN Tuesday June 30th at 6PM ET Looking forward to seeing you on the call!