implementation

Multimodal Setup with Google ADK

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

Linked challenge: Multimodal Energy Transition Advisor with Google ADK and Voiceflow

Format

Text-first

Lines

Sections

Linked challenge

Multimodal Energy Transition Advisor with Google ADK and Voiceflow

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Using Python and the Google ADK, initialize an agent that uses Gemini 1.5 Pro. Define a tool called 'AnalyzeEnergyChart' that takes an image of a BloombergNEF energy transition chart and returns a structured summary of the investment growth in 2025 ($2.3 Trillion).

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.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Multimodal Energy Transition Advisor with Google ADK and Voiceflow

Global energy transition investment hit a record $2.3 trillion in 2025. Navigating this complex landscape requires processing vast amounts of visual data (charts, maps) and text-based policy reports. In this challenge, you will use the Google Agent Development Kit (ADK) to build a multimodal advisor. This agent will leverage Gemini 1.5 Pro to interpret commodity charts (like BloombergNEF's '10 Numbers to Watch') and infrastructure plans (like the $8B Massachusetts transportation investment). To make this technical system accessible to stakeholders, you will integrate the backend with Voiceflow to create a voice-enabled interface. The Google ADK will handle the 'heavy lifting' of multimodal reasoning—analyzing the S&P Global charts on CPC Blend crude and Venezuelan heavy crude shocks—while Voiceflow orchestrates the user interaction, allowing energy analysts to query the data through natural speech or text.

Open challenge

Related prompts

Browse library

Initial Assessment Prompt

planning

Content Classification Prompt

implementation

Problem Definition and Requirements Gathering

To establish a clear understanding of the problem space and define comprehensive requirements for the AI solution.