Back to Prompt Library
implementation
Integrate Across AI for Persistent Memory
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Real-time Crypto Fraud Alert Agent with Claude Agents SDK
Format
Text-first
Lines
1
Sections
1
Linked challenge
Real-time Crypto Fraud Alert Agent with Claude Agents SDK
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Explain how you would integrate 'Across AI' to provide your Claude agent with persistent memory. This memory should store historical fraud patterns, suspicious addresses, and previously identified social engineering tactics. Describe how the agent would consult this memory before making a detection decision, and how it would update the memory with new information. Provide conceptual code/API calls for interacting with Across AI within the Claude agent's workflow.
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.