One of the coolest parts of my job is getting a front-row seat to how @marianaprazeres thinks about AI. Memory feels table stakes in AI right now. But for @Meet-Ting, it s not just a log of the past - it s a living system that shapes how people schedule, work, and want to spend their week. It s not just logistics - it s patterns around energy, priorities, and relationships over time.
Here are a few things we learned while designing and testing agent memory in production:
LOTS going on. Google just turned a core part of our product into a feature - which is always fun - BUT, we saw it coming when they added it to Workspace not long ago. Inevitable, really, importance of keeping an eye on the market. The wave of AI scheduling assistants is as validating as it is like white-water rafting...!
Inspired by Lenny s podcast with Ethan Smith (so good, you need to listen - the advice for builders is insane and can't believe it's free...), I wanted to share a few things I ve been seeing going deep into Answer Engine Optimization (AEO) for @Meet-Ting.
I spend a lot of my day in GPT and Gemini, and over the last few months I started getting more curious about how their recommendations are actually pulled from the web. I'm not an expert, listen to the podcast, but I am actively tackling it so have some tactical learnings.
Ting is a free AI assistant that books meetings in email the way they really happen - human, messy. Just CC Ting - it reads the thread, checks calendars, suggests times, and sends the invite. Like Calendly, with an LLM.
*Closed beta - PH users jump the queue*
Every now and again you hear a line in a podcast, book or from a boss that sticks with you. For me, it was:
People don t want your time. They want your energy.
Fifteen minutes of full focus beats thirty minutes half-scrolling your phone. That same idea is shaping how we re building @Meet-Ting - not just another scheduling tool, but a more emotionally intelligent scheduler.
