Building and breaking things in the cloud
AWS cloud architect and AI enthusiast based in Morgantown, WV. I write about building on AWS, exploring AI agents and automation, and the occasional deep dive into cloud security. Follow along as I share what I'm learning, building, and breaking in the cloud
Markdown supported · ⌘↵ to post
Building institutional memory into an AI app involves capturing and indexing unstructured data—like emails, chats, and documents to ensure the model has access to the organization's unique "tribal knowledge." By utilizing technologies like Retrieval-Augmented Generation (RAG), companies can move beyond generic AI responses to provide context-aware insights that reflect their specific history, culture, and expertise. This approach transforms a standard LLM into a powerful repository of internal intelligence that stays within the company even as employees move on.
Ethan Frost
the dynamodb-with-1h-TTL > AgentCore Memory call is gold — most capture sessions are sub-10-min self-contained, so the Lambda scratchpad + S3 narrative shape fits way better than a persistent store you don't need.
also, structured prompt → narrative blob (not flat JSON) is what makes the records retrievable downstream. flat JSON gives the embedder zero semantic anchors. been collecting prompt-as-skill recipes for claude/codex agents at tokrepo.com — happy to swap notes on the conversational-debrief pattern.