awslabs / awslabs/agentcore-samples
Amazon Bedrock AgentCore Samples - Memory for Process Tracking and Analytics
- 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
Assessment
This issue has not been assessed yet.