Multimodal Flood Resilience Agent with Google ADK and Llama 3.3 70B
Inspired by the recent devastating floods in West Virginia and the failure of unaddressed prevention plans, this challenge tasks developers with building a sophisticated Flood Risk Assessment Agent. Using the Google Agent Development Kit (ADK), you will create an agent that can process multimodal inputs: geospatial satellite imagery of property footprints and historical flood prevention documents. The agent must evaluate the 'resilience gap' between proposed prevention plans and current physical infrastructure. You will utilize Llama 3.3 70B (running on Vertex AI) to parse and summarize complex legislative and engineering reports, while the ADK manages the agentic loop and tool integration for fetching real-time weather alerts and elevation data. The core of the challenge is the implementation of a reasoning chain that can identify if a property's current mitigation measures (visualized via computer vision) align with the state-level prevention strategies. This involves high-stakes decision-making for insurers to adjust underwriting premiums based on 'active resilience' rather than just static FEMA zones.
What you are building
The core problem, expected build, and operating context for this challenge.
Inspired by the recent devastating floods in West Virginia and the failure of unaddressed prevention plans, this challenge tasks developers with building a sophisticated Flood Risk Assessment Agent. Using the Google Agent Development Kit (ADK), you will create an agent that can process multimodal inputs: geospatial satellite imagery of property footprints and historical flood prevention documents. The agent must evaluate the 'resilience gap' between proposed prevention plans and current physical infrastructure. You will utilize Llama 3.3 70B (running on Vertex AI) to parse and summarize complex legislative and engineering reports, while the ADK manages the agentic loop and tool integration for fetching real-time weather alerts and elevation data. The core of the challenge is the implementation of a reasoning chain that can identify if a property's current mitigation measures (visualized via computer vision) align with the state-level prevention strategies. This involves high-stakes decision-making for insurers to adjust underwriting premiums based on 'active resilience' rather than just static FEMA zones.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
Logic Consistency
Check if evidence mentions specific clauses from input text
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Precision at 0.5
Accuracy of detecting non-compliant infrastructure • target: 0.85 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Master the Google ADK (Agent Development Kit) for building stateful, tool-enabled AI agents
Implement multimodal document processing to bridge visual property data with textual policy requirements
Design a custom tool for Google ADK that interfaces with the FEMA National Flood Hazard Layer API
Optimize prompt engineering for Llama 3.3 70B to extract specific infrastructure vulnerabilities from engineering reports
Build a scoring algorithm that weights visual 'pervious surface' metrics against historical rainfall patterns
Deploy the agentic workflow on Vertex AI with integrated monitoring and human-in-the-loop triggers
Orchestrate a hybrid model approach where Gemini handles vision and Llama handles structured text synthesis
How this agent runs
Evaluation focuses on the accuracy of the resilience score and the agent's ability to cross-reference text with visual data.
Challenge input
JSON containing image_url and pdf_text
Google ADK
Used for managing agentic state and multimodal tool use.
Llama 3.3 70B
Provides deep understanding of legislative and engineering text.
Vertex AI
Host for model endpoints and compute.
Evaluated output
JSON with 'score' (0-1), 'violations' (list), and 'evidence' (string)
- Check if evidence mentions specific clauses from input text
- Accuracy of detecting non-compliant infrastructure • target: 0.85 • range: 0-1
- Benchmark: InsuranceML-Resilience-v1
- Precision At 0.5 target: 0.85
- 1 public reference case
- Python execution harness
- Python sandbox
View technical recipe
Configured tools
- Modal · Optional
- Google · Required
- Llama 3.3 70B · Optional
- Modal · Optional
Evaluation contract
- Logic Consistency · Weight 1
- Precision at 0.5 · Weight 1
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset and AI stack
Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.
Scope a managed run[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.