planning

System Design for Multi-Agent Foresight

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

Linked challenge: Multi-Agent Foresight for Resilient Urban Infrastructure Planning with Command R+ & AutoGen

Format

Text-first

Lines

Sections

Linked challenge

Multi-Agent Foresight for Resilient Urban Infrastructure Planning with Command R+ & AutoGen

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Design the architecture for a multi-agent system that can perform foresight-driven urban infrastructure planning. Specify the roles of at least four distinct agents (e.g., Data Analyst, Infrastructure Planner, Risk Assessor, Policy & Ethics), their communication protocols using AutoGen, and how they will integrate with a multimodal semantic memory system using a vector database. Detail how Command R+ via Amazon Bedrock will be used by each agent for their specific reasoning tasks and how agent debate will resolve conflicts or optimize decisions.

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.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

planning

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

Linked challenge

Multi-Agent Foresight for Resilient Urban Infrastructure Planning with Command R+ & AutoGen

Design and implement a multi-agent system capable of performing 'foresight' for urban infrastructure planning, with a specific focus on resilience against extreme weather events. The system should leverage Command R+ via Amazon Bedrock for advanced reasoning, integrate a grow-and-refine multimodal semantic memory, and employ a multi-agent debate mechanism for risk-aware decision-making. Developers will simulate a scenario where agents analyze diverse data sources (e.g., historical weather patterns, spatial infrastructure maps, urban planning documents) to propose resilient infrastructure solutions, identify potential failure points, and debate the optimal strategies, mimicking the principles of agentic learning and risk-aware planning. The core of this challenge involves orchestrating specialized agents – a Data Analyst Agent, an Infrastructure Planner Agent, a Risk Assessment Agent, and a Policy & Ethics Agent – using AutoGen. These agents will communicate, share insights from their multimodal memories, and engage in structured debates to arrive at comprehensive, foresight-driven recommendations. The multimodal semantic memory, backed by a vector database, will store and retrieve information in various formats (text, images, geospatial data), enabling the agents to build a rich understanding of the urban environment and potential future scenarios, thereby bridging the gap from simple prediction to proactive foresight.

Open challenge

Related prompts

Browse library

Problem Definition and Requirements Gathering

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

AI Solution Architecture and Strategy

To create a comprehensive technical architecture and AI strategy that guides the implementation of the solution.

Implementation Plan and MVP Development

To provide a clear, actionable roadmap for implementing the AI solution from concept to deployment.