Back to Prompt Library
implementation
Define Mastra Agent with Memory
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Cognitive Memory Agent for Visual Content with Mastra AI and MemGPT
Format
Text-first
Lines
1
Sections
1
Linked challenge
Cognitive Memory Agent for Visual Content with Mastra AI and MemGPT
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Initialize a new Mastra AI agent using TypeScript. Configure it to use GPT-5.4 Pro as the default model. Integrate a MemGPT tool that allows the agent to call functions for 'save_preference' and 'retrieve_preferences'.
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.