Back to Prompt Library
implementation

Develop Proactive Prompt Generation

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

Linked challenge: GPT-5 Ephemeral Content Intelligence with MCP & Adaptive Thinking

Format
Text-first
Lines
1
Sections
1
Linked challenge
GPT-5 Ephemeral Content Intelligence with MCP & Adaptive Thinking

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Extend your agent to not just analyze, but also proactively generate personalized and helpful prompts or replies. Based on the analysis of a 'ghost post' (e.g., sad sentiment, asking for advice), the agent should craft a contextual and empathetic response that respects the 'unfiltered thoughts' aspect. Use GPT-5 for generating these prompts, integrating its ability to maintain a supportive tone.

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.