Ritik Kumar

Ritik Kumar

Pryveo | AI memory & context for teams

About

I run growth at Pryveo (pryveo.com). We're building shared memory for AI tools, so you and your team stop re-explaining the same context to every chat. Here to discover new products, learn from other makers, and talk about AI agents, context, and knowledge work. I always try to leave honest feedback on launches I like. Say hi on X or LinkedIn.

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking
Gone streaking 5
Gone streaking 5

Forums

•

3d ago

how do you tell the agent what changed since the last session?

someone on my last thread pointed out the project file says what the project is, but not what changed since yesterday. i don t have a good answer for that yet.
what do you do, just let it read the git log?

•

3d ago

asked how you keep context between agent sessions, 8 people answered and nobody said the same thing

i asked here yesterday how people keep their agents from forgetting between sessions. almost everyone said a file in the repo.
what i took from it: never trim the file, keep the rejected idea next to the decision, small checkpoints, and make the agent write the failing test first.
mine still re-reads everything every time, so checkpoints is what i m trying next.
what does your agent still forget even with all this?

•

5d ago

How do you keep AI up to speed on your project?

I keep running into this while building with AI: after a few sessions, I end up re-explaining the project, the decisions we made, and what changed.

How do you handle that? Do you keep a project file updated, rely on chat history, or have another system that works?

View more