Why This Matters

Over the years, LLM users have learned how to prompt LLMs effectively, using tricks like prompt chaining.

With Pieces Long-Term Memory, you can add more dimensions to your prompts, querying across captured memories using keywords related to your activities, applications, or time periods.

These guides show how to query the stored LTM context using the Pieces Copilot in the Pieces Desktop App or any app with a Pieces plugin or extension.

When using these prompts, ensure you have LTM-2.7 turned on, both the [LTM](/products/core-dependencies/pieces-os/quick-menu#ltm-2-engine), and the LTM context source in the copilot chat.

Guide Links

These guides introduce some of the ways you can query the databased of stored LTM-2.7 context using the Pieces Copilot in the Pieces Desktop App, or any of the applications you use that have a Pieces plugin or extension.

Click one of the cards below to jump to that guide.

Examples of the typical use cases we see for Pieces LTM with the kinds of prompts users ask. A selection of popular use cases for the new Pieces Workstream Activity view. Some general prompting tips to help you get the most out of Pieces.