Back to Prompt Library
implementation
Google ADK Multimodal Agent Configuration
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Multimodal Plant Diagnostics Agent using Google ADK & Llama 3.3 70B
Format
Text-first
Lines
1
Sections
1
Linked challenge
Multimodal Plant Diagnostics Agent using Google ADK & Llama 3.3 70B
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Using Google ADK, instantiate an `Agent` initialized with Gemini/Llama vision endpoints. Register a multimodal input processor capable of decoding base64 image streams into tensor inputs.
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.