---
title: "Comment by Ethan Frost on \"Building Institutional Memory Into Your AI App: Capturing Unstructured Decision Data with Amazon Bedrock Knowledge Bases\" | Hashnode"
description: "the dynamodb-with-1h-TTL &gt; AgentCore Memory call is gold — most capture sessions are sub-10-min self-contained, so the Lambda scratchpad + S3 narrative shape"
url: "https://hashnode.com/posts/building-institutional-memory-into-your-ai-app-capturing-unstructured-decision-data-with-amazon-bedrock-knowledge-bases/69f29d946e0124c05e7f379b/comment/69f2ee19124bcf782af4b557"
---

[Discussion](https://hashnode.com/posts/building-institutional-memory-into-your-ai-app-capturing-unstructured-decision-data-with-amazon-bedrock-knowledge-bases/69f29d946e0124c05e7f379b)

Comment [Building Institutional Memory Into Your AI App: Capturing Unstructured Decision Data with Amazon Bedrock Knowledge Bases](https://hashnode.com/posts/building-institutional-memory-into-your-ai-app-capturing-unstructured-decision-data-with-amazon-bedrock-knowledge-bases/69f29d946e0124c05e7f379b)

[Ethan Frost](https://hashnode.com/@ethanfrost)

[Apr 30](https://hashnode.com/posts/building-institutional-memory-into-your-ai-app-capturing-unstructured-decision-data-with-amazon-bedrock-knowledge-bases/69f29d946e0124c05e7f379b/comment/69f2ee19124bcf782af4b557)

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.
