Back to Prompt Library
implementation

Implement Gemini 2.5 Pro Integration for Plan Generation

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

Linked challenge: Multi-Modal Image Editing Agent

Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Modal Image Editing Agent

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Implement the 'Plan Generation' state where Gemini 2.5 Pro receives the multi-modal input (text description, potentially an initial image analysis) and generates a detailed, step-by-step editing plan. This plan should include specific tool calls and parameters. How will you handle ambiguities or requests requiring 'extended thinking'?

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.