AI as a Mini-Product Manager
Hey folks, I'm Yuval. I run a tiny startup called Glitter AI. It's just me full-time here, with a couple of freelances to help here and there. A couple of months ago, I went from managing zero requests to hundreds -- overnight (won Product of the day on Product Hunt). As someone who gets VERY easily distracted (maybe you relate), I had to find some sort of way of handling all the chaos if I didn't want to burn out. I came up with a pretty cool automation flow that I thought folks on HN here may be interested in reading about :) So here goes: Most of my interactions come through Intercom.…
What it does
In the maker’s words, at launch
Hey folks, I'm Yuval. I run a tiny startup called Glitter AI. It's just me full-time here, with a couple of freelances to help here and there. A couple of months ago, I went from managing zero requests to hundreds -- overnight (won Product of the day on Product Hunt). As someone who gets VERY easily distracted (maybe you relate), I had to find some sort of way of handling all the chaos if I didn't want to burn out. I came up with a pretty cool automation flow that I thought folks on HN here may be interested in reading about :) So here goes: Most of my interactions come through Intercom. After the product hunt launch, I got waves of bug reports and feature requests. So I link every incoming message to a webhook. I do manually trigger this step through Intercom after replying to the customer (so there's context for the AI - more on that in a bit), but then everything from there on out is automatic. Next, Make.com grabs the conversation details and runs them through prompts that guide OpenAI to "act like a savvy product manager." The task is to act like a customer-support-rep-meets-PM: parse and summarize conversations into actionable points—be it a bug report, feature request, or feedback (I'll include a link to a post with the full prompt below). But summarizing wasn’t enough. I needed this flow to live somewhere, and to categorize everything. I chose Notion, but it could have just as easily been Airtable or the likes (or Excel, honestly). I call the space in Notion my "Second Brain." Once in Notion, every request is linked back to its original Intercom conversation, which helps me quickly see patterns like repeated feature requests or pesky recurring bugs. It’s like having a high-level map of what users need. Then in Notion I do manually quickly go through the summary and tags to ensure everything is in place. I then attach those clean summaries to existing pages using a variation of the RICE framework to prioritize my action items. Every page counts the number of requests linking to it, so I can keep track of recurring bug reports / feature requests / product feedback etc and prioritize accordingly. I can't include screenshots here, so I'm linking to my original post. It's mostly the same content as here, but with the prompt and a bit more detail, if you're interested: https://www.glitter.io/blog/how-i-use-ai-and-automation-to-r...
Does the same job
all alternatives →- IMI Made an AI Software Engineer with Google Gemini 1.5 Flash2024 · saas-quick.com · ▲6
Hey HN! Thank you for all the support and feedback on my original submission 2 months ago. I've been improving the backend using a MCTS/AlphaZero approach and it's currently producing much better results. My long term goal is to allow users to manage multiple projects, deployed autonomously, both from scratch and by making continual updates all prompted with natural language. The cost of each project has been lowered to $9 as performance with smaller models has improved (I migrated from Claude-3-Opus to gemini-1.5-flash). Thanks for checking it out!
- PAProduct as Code – YAML-based product management for AI coding workflows2025 · productascode.org · ▲9
I have worked with AI assistants for a while, and while I am really excited about it, there were times when I felt really frustrated. LLM would end up in a loop with no end. This is when I started experimenting with creating work plans. Initially simple todo list, but it felt like "product vibing", so a bit more sophisticated later on. I started seeing value in it. The one day it hit me. Why not use the same GitOps principles to managing product tickets? I started playing with that and really liked the way it worked. After a chat with a friend of mine, I realised that a standard or a spec…
- IBI built a way to find and install Claude skillsJun 2026 · claudinho.xyz · ▲7
I've been experimenting with ways to increase AI adoption for non-technical people. Basically, all companies are pushing for AI because it's all over the news and they feel left behind but most people have no clue where to start. I think 90% of people (ie non coders) are sufficiently well served by using cowork instead of claude code or something similar. If we can get people from sales, customer support, marketing, etc to collaborate with skills and cowork to form a company brain, I think it's gold. So I think there's opportunity for the community to share skills that work well for 1000s of…
- CWChat with AI to Find Your Dream Job2023 · maching.ai · ▲5
Hey HN friends, Just launched my first NoCode web app, maching.ai, built with Bubble. Check it out and let me know if you have any questions or suggestions!
- YAYou are now the product manager of this siteJan 2026 · youarethepm.com · ▲6
Hey HN, I wanted to see what happens if you put a large group in control of a site that’s completely built and updated by an AI agent. See the site here: https://youarethepm.com. I first tried this with a small group of co-workers and it worked surprisingly well, so the obvious next step was: give it to a bigger group of strangers and see what we learn. This site is fully autonomous. An AI agent reads this thread, decides what to do, writes code, and ships updates on a virtual computer. I might step in if it gets totally stuck, but the goal is for the site to evolve primarily based…
- IBI built an AI personal assistant that picks up your calls2025 · apps.apple.com · ▲5
hey hacker news! no matter what I have tried, nothing actually got rid of spam calls. built an AI agent that picks up your phone to filter out these spammers dynamically. next on the roadmap is automating scheduling
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
