I am looking to use a digital audio recorder to take audio for 8-10 hours straight and dump it into an ai for analysis. would a chat system work, do i need to program something, or is there an ai platform/software that can do heavy lifting like this? I understand the privacy concerns. client wants to carry an "always on" recorder in a single-party state and have the day analyzed, parsed, summarized, and converted to actions that are automated vs his new todo.

Client currently uses Fireflies and Claude. We are trying to build an integrated pipeline where fireflies input will be pushed into Claude, and commands will update the Bigin CRM. We have everything set-up except for the fireflies>Claude automation. at this point, using Claude to pull data from FF is fine, but its not clean. any advice or a quote on something that is already complete would be great!! Client wants voice (notes, meetings, calls, etc) to create and update workflows, CRM, todos, etc.

Hey everyone, I’ve been working on a simple AI workflow using n8n and DeepSeek R1 (the free model), and I'd definitely need some help. Here’s what I’m trying to do: - A user submits a YouTube video link - I use Apify to transcribe it - Then I send the transcript to the LLM - The goal is to generate a LinkedIn-style post based on the video content It worked once. One of the early posts actually came out great, sharp, and on point. I was happy. Then I tried a different video… and everything fell apart. Now I’m getting posts that are vague, generic, or completely miss the point. It’s been over a week of trial and error. I’ve rewritten the system prompt like 30 times - changing wording, tone, structure, nothing sticks. Sometimes I get decent output. But most of the time, it’s way off. So I’m stuck, and I’m starting to wonder if it’s the way I’m prompting or if this model just isn’t capable for this kind of task. If anyone here has built a content-writing agent that works reliably or in production right now, I’d love to know: - How do you write a system prompt that holds up across different inputs? - Is there a framework or method that helped you make it consistent? - Is switching to GPT-4, Claude, or another paid model would solve this? - And how do you actually test/improve these prompts without losing your mind? Not looking for theory or general AI advice, just real-world experiences from people who’ve actually built something like this and made it work. Would really appreciate any input. Thanks 🙏

Still waiting for inspiration to strike. We will see what happens

Hey team, Off the back of your feedback, we’ve made some changes to the community layout to make things simpler, more intuitive, and easier to navigate. The goal is to eliminate second-guessing about where to post and help you get the most out of the space. Here’s what’s changing: 📌 Announcements Your go-to channel for all major updates. I’ll start sharing more content on what we’re building across the AAA Accelerator and Morningside AI, so you can directly learn how I am growing my companies and get inspired to grow your own. This is where I will share my latest YouTube videos as well. Check this regularly so you’re always in the loop. 🧠 Business & Strategy Use this to talk about your offer, marketing strategies, business models you're exploring, and get feedback from others building too. 🤖 Tech & Tools All things tech: automation, dev, tools, workflows. Keep the nerd talk here. 🏆 Wins Big or small, share them here. Let’s hype each other up. 🎥 YouTube Resources As always, your go-to channel for all the resources I use, coming from my YouTube videos. 🧰 Job Board / Hiring Hiring? Looking for work? Offering your skills? Post it here. ❓ Ask for Help Stuck on something? Drop your question here and let the community jump in. This is a community-led channel so don’t be afraid to ask or dissect problems together. These changes go live in the next 24-48 hours. If you have any open threads or discussions you want to save, please do that now. Let’s keep it sharp and make this space work even better for all of us. Liam 💪