Strong framing. I keep seeing teams treat this as a model problem when it is really an operational-memory problem: prior decisions, constraints, docs, transcripts, and email live outside the agent, so humans become the manual context layer.
Curious what you see as the hardest part in practice: remembering, retrieval quality, or trust/provenance? And do teams treat this as urgent enough to budget for, or still more like infra they hack around?
https://knowledgenetworks.substack.com/p/david-cross-explains-ai-native-thinking?r=7ykchg&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
Hey! What's your question or topic suggestion? This chat is for discussing TAE issues and suggesting future topics.
Strong framing. I keep seeing teams treat this as a model problem when it is really an operational-memory problem: prior decisions, constraints, docs, transcripts, and email live outside the agent, so humans become the manual context layer.
Curious what you see as the hardest part in practice: remembering, retrieval quality, or trust/provenance? And do teams treat this as urgent enough to budget for, or still more like infra they hack around?