by yuvalkarmi on 9/22/2024, 4:55:47 PM with 3 comments
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.
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...