Hey everyone! 👋 Quick heads-up for Tuesday's call, I've been building something I'm calling RecapFlow, and I'm going to do a little show-and-tell. You know how after each call someone has to pull together a recap and write up the community post? I built a pipeline to automate all of that, it grabs the transcript, merges it with the chat log, runs it through a chain of prompts, and generates the posts automatically. Tuesday's call will actually be the first one processed by RecapFlow, so you'll get to see the results in real time! I also documented the whole thing as a reference architecture, which is live at recapflow.patchoutech.com 📎 On Tuesday I'll walk through: 🔄 How the pipeline works end-to-end (from Zoom call to Skool post) 🛠️ The n8n workflows that make it happen 🧠 The prompt chain that distills a 2-hour call into something you'd actually want to read 📝 The reference docs, so if you want to build something similar, you've got a head start Whether you're into automation, prompt engineering, or just curious how the sausage gets made, this one's for you. See you Tuesday! 🎙️

Developing an app MVP for the fall time-frame - using NotebookLM (app knowledge base docs) and a separate Notebook (app design artifacts) for the “Project Brain”. Taking the next steps in Firebase Studio to use the Project Brain with Gemini/Conductor plugin to build the project (web application) - experiencing all sorts of Gemini hallucinations and dead ends without Conductor - any experiences with this type of setup?

It’s a GitHub App that listens to webhook events and helps automate common repository tasks like PR review, issue triage, and repo health checks. I tried to focus more on architecture reliability — guardrails, async webhook handling, and validation of AI responses. Would love feedback from other developers on the approach. Repo: https://github.com/Shweta-Mishra-ai/github-autopilot

Hey, guys! I need your help. 😭 I’m a Machine Learning intern, and I built an application in Vertex AI Studio in one GCP project. The problem is that we couldn’t connect it to BigQuery because of a service account error (everyone on my team tried and we all failed). My manager asked me to recreate the application in Vertex AI Studio, but in a different project. I’m doing that now, but even using the exact same prompts from the original project, the new version isn’t performing nearly as well. I know some variation is expected with generative AI, but the original version was so good that I don’t want to give up on it. I downloaded the ZIP file with the code from the original application — is there a way to upload/import what I already have into the new project so I can keep the same behavior?

Per the call yesterday, here are some screenshots from my auto-generated Help, Product Updates (Generated from GitHub updates translated by AI to user speak), and product suggestions sections. Doing what users need doesn't need to be a chore and yet another thing that Claude Code can master for you.