Hey Architects! I've turned the Friday call into a 1-on-1 Q&A with me directly. Come ask questions on AI, agents, coding, business or anything on your mind. See what others are building too. >> Add it to your calendar << See you there!

For the past month, I've been switching between Fable and GPT Sol 5.6 medium for implementation and planning. Both Fable and Sol are great for planning. Sol is rock solid for implementing, with its attention to detail and price. Outside of those two, what other models are you having success with?

Trying to decide between Supabase, Convex, Neon, or Turso? Wondering if your "second brain" setup is actually doing what you think it's doing? This is the room where that gets hashed out live — real trade-offs, real war stories, zero guessing. Bring your stack. Someone's already made the mistake you're about to make. Fridays, 9 AM Pacific. 🔗 https://us06web.zoom.us/j/86132599751?pwd=mzYuc4I29WPGCvG091frYPREatrVXo.1

I’ve been hearing some good things about it online. Has anyone here tried it yet? I’d love to hear your first impressions.

Hey Architects, As projects get bigger, AI can make things confusing if it doesn’t understand your app. For example, you might end up with two similar backend files that do the same job. To save yourself some time, before a major change or fix, ask this: 1. What’s the blast radius? 2. Is this the lowest-risk option? This usually gives the LLM a chance to audit the code and present a lower-risk option. Try it on your next risky change and tell me if it saved you a debug session. — BONUS: Here's a prompt I've used for the past 6 months. It's worked well, but I use it less now that I ask those two questions above. Try both and see which you like better. --- The Prompt: "Sanity check for our review: - Preserves all existing functionality - Minimal change, no scope creep - Reduces brittleness, doesn't add it - Simplest viable approach - No new source of truth unless explicitly requested Confirm or provide an improved plan — do not implement."