everything everywhere, all at once
Joined September 2025
- Tweets132
- Following33
- Followers506
- Likes225
Last week a user told us memory.store gave her a wrong answer.
Thanks to memory.store she also knew where the mistake came from. This was a bad memory where the document made it seem like the conclusion was x when in reality it was y.
She wanted her answers fixed but the clarification should only be required once.
This was the feedback for us. She wants to teach the agent.
For an agent with persistent memory, customer feedback is the ultimate loop. Wrong answer in, correction in, better answer out for all future calls.
The people who use the agent know which answer is wrong. This is why your memories need to be seen both by the human and the agents.
We've shipped inline correction for briefs. Update your briefs and pause them when you need to.
every conversation, every single day
without memory!
even inside projects you have to explain your context again and again
we built an integration with fathom (an ai meeting note taker).
this would sync all your meetings context into one place, and you can use those insights while chatting claude.
@HamadaSalhab explaining everything in detaill.
writing from memory "write a blog post about active memory vs storage."
cowork pulled from philosophy notes, product decisions, and a forgotten 3am idea fragment.
the draft read like it was written by the person who took the notes. because it remembered what they'd already thought.