Back to Prompt Library
planning
Google ADK Agent Definition for Multimodal Content
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Multimodal Content Generation Agent for AI Video Platform
Format
Text-first
Lines
1
Sections
1
Linked challenge
Multimodal Content Generation Agent for AI Video Platform
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Define the core structure of your Google ADK agent for multimodal content generation. Outline its primary objective, the types of inputs it will accept (e.g., text for trends, image/video for inspiration), and the expected outputs (e.g., video concepts, scripts). Describe how Gemini 2.5 Pro will be used for multimodal reasoning and creative text generation. Provide an initial Python snippet showing how to initialize the ADK client and potentially a basic agent loop.
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.