Back to Prompt Library
implementation

Implement Long-Term Memory with ChromaDB

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Proactive Voice Safety Assistant

Format
Text-first
Lines
1
Sections
1
Linked challenge
Proactive Voice Safety Assistant

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Set up ChromaDB to store and retrieve user-specific information (e.g., name, past topics of interest, preferred communication style, last check-in date). Modify your Claude Sonnet integration to leverage this memory, personalizing greetings and conversation topics based on historical data. Demonstrate this with the 'PersonalizedCheckin' task.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.