Back to Prompt Library
planning

Design Semantic Kernel Workflow

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

Linked challenge: Preventing LLM Data Memorization & IP Leakage with Semantic Kernel

Format
Text-first
Lines
1
Sections
1
Linked challenge
Preventing LLM Data Memorization & IP Leakage with Semantic Kernel

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design a Semantic Kernel plan that first calls Claude 3.7 Sonnet to generate content based on a user prompt, and then invokes a custom skill to check the generated content against a LlamaIndex-powered knowledge base for originality. Detail the plugins and connectors required.

Adaptation plan

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

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.