Lamis
A member of the technical team at Anthropic, focusing on research into context engineering and Agent memory systems. Has previously spoken at AI DevCon.
Timeline (last 90 days)
Anthropic technology team member Lamis systematically reviewed the evolution path of Context Engineering over the past year at AI DevCon.
Lamis divides memory work into two complementary paths: in-session memory (the agent reads and writes memory within a single session) and out-of-session "Dreaming" (a separate agent batch-reviews historical session records and modifies the memory store).
The gradual rollout path Lamis outlined is: first use simple means such as Claude MD and skills; when the number of agents grows, run cycles lengthen, and collaboration becomes more complex, introduce production-grade mechanisms such as versioning, hashing, and tiered permissions; finally consider adding out-of-session processes like Dreaming.
Lamis said this memory system approach is not only applicable to programming tasks—he himself uses the memory system to capture his writing preferences and slide style for presentations.
Lamis acknowledged that the team is bringing back practices proven in software engineering (version control, concurrency control, deterministic execution), on the premise that these mechanisms can be used efficiently by autonomous agents.
All Facts (5)
Lamis divides memory work into two complementary paths: in-session memory (the agent reads and writes memory within a single session) and out-of-session "Dreaming" (a separate agent batch-reviews historical session records and modifies the memory store).
50%UnverifiedThe gradual rollout path Lamis outlined is: first use simple means such as Claude MD and skills; when the number of agents grows, run cycles lengthen, and collaboration becomes more complex, introduce production-grade mechanisms such as versioning, hashing, and tiered permissions; finally consider adding out-of-session processes like Dreaming.
50%UnverifiedLamis said this memory system approach is not only applicable to programming tasks—he himself uses the memory system to capture his writing preferences and slide style for presentations.
50%UnverifiedLamis acknowledged that the team is bringing back practices proven in software engineering (version control, concurrency control, deterministic execution), on the premise that these mechanisms can be used efficiently by autonomous agents.
50%UnverifiedAnthropic technology team member Lamis systematically reviewed the evolution path of Context Engineering over the past year at AI DevCon.
50%