awslabs / awslabs/agentcore-samples

Amazon Bedrock AgentCore Samples - Memory for Process Tracking and Analytics

Open
#1,093 0 comments 0 reactions 1 assignee Claimed by @akshseh View on GitHub
01-tutorials Tutorial Request
Dominant language
Python
Stars
3.4k
Forks
1.3k
Avg merge
1d 22h
Merged PRs (30d)
30

Description

**Describe the tutorial request**
Add a new advanced pattern tutorial for AgentCore Memory: "Memory for Process Tracking and Analytics".

```
Add a new advanced pattern tutorial for AgentCore Memory: "Memory for Process Tracking and Analytics" (Part 1 of 2).

This notebook demonstrates using memory namespace hierarchies combined with record transitions to implement state-machine-like behavior for tracking business process lifecycles (e.g., credit card recommendation pipelines). Namespaces themselves are storage — the state machine pattern emerges from how we structure namespace paths to represent stages and move records between them. It covers:
- Creating memory and populating it externally (not from conversations)
- Using namespace path hierarchies to represent business process states (pending → shown → accepted → declined → applied)
- Transitioning records between namespaces with audit history
- Querying namespace data for product-level analytics
- Combining namespace queries with LLM analysis for natural language insights
- Viewing customer-specific journeys across stages

Part 2 will build on these patterns to enable real-time analytics and hyper-personalisation.

```

**Is this feature already supported by the AgentCore service?**
- [X] Yes
- [ ] No

If `yes`, please provide any appropriate documentation link.
https://docs.aws.amazon.com/bedrock-agentcore/latest/APIReference/API_BatchCreateMemoryRecords.html

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.