4 Comments
User's avatar
Mykola Kondratuk's avatar

receipts over memory makes sense for agent reliability. harder question on the team side is who decides what context the agent keeps between sessions - nobody seems to own that call.

The AI Runtime's avatar

"But production systems often need more than that." Each system has different needs and hence the struggles

Gringo B's avatar

This is Nate B Jones‘ content all day. Shameless copy without mentioning the real author.

Sumant Thakur's avatar

Hey, Thanks for pointing that out! But I don't even know the author you are talking about, and if you read the complete post I have added original link to research papers.

Will be really helpful if you can share the link of the author you have mentioned!