Skip to main content
Back to Prompt Library
implementation

Google ADK Agent Definition

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

Linked challenge: Deepfake Identity Verification Triage Pipeline with Google ADK and Contextual AI

Format
Code-aware
Lines
4
Sections
3
Linked challenge
Deepfake Identity Verification Triage Pipeline with Google ADK and Contextual AI

Prompt source

Original prompt text with formatting preserved for inspection.

4 lines
3 sections
No variables
0 checklist items
Initialize a Google ADK agent with Gemini Multimodal capabilities. Define a custom Contextual AI tool to ground extracted document fields against standard verification records.

from google.adk.agents import Agent
from google.adk.models import GeminiPro

# Instantiate agent and configure Contextual AI grounding step

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.