planning

System Architecture Setup

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

Linked challenge: Multi-Agent High-Entropy Alloy Discovery with AutoGen and Langbase

Format

Text-first

Lines

Sections

Linked challenge

Multi-Agent High-Entropy Alloy Discovery with AutoGen and Langbase

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Initialize three AutoGen agents using Langbase Pipes. 1) ArchitectAgent: Responsible for proposing Cr-Mn-Fe-Co-Ni ratios. 2) PhysicsAgent: A tool-enabled agent that calculates ΔSmix (Mixing Entropy). 3) CriticAgent: Validates if the composition is stable and durable based on the 'Nature Materials' study criteria (subnanoscale durability). Use the following Langbase pipe configuration: 'lb_pipe_discovery_v1'.

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 High-Entropy Alloy Discovery with AutoGen and Langbase

Inspired by the rapid synthesis of subnanoscale high-entropy alloys (HEAs) with ultrahigh durability, this challenge tasks you with building a multi-agent discovery pipeline. You will utilize Microsoft's AutoGen framework to orchestrate a conversation between a 'Materials Architect' agent, a 'Physics-Informed Surrogate' agent, and a 'Stability Analyst' agent. The goal is to identify optimal atomic ratios for a five-element alloy (Cr-Mn-Fe-Co-Ni) that maximizes both durability and thermal stability. To ensure high-performance inference, you will integrate Langbase to host and manage your large language models (LLMs) as 'Pipes'. The system must utilize a physics-informed surrogate model—approximated via prompt-engineering and tool-calling—to evaluate the mixing entropy and enthalpy of proposed compositions. Your orchestration will focus on iterative refinement where agents critique proposed chemical configurations against real-world thermodynamic constraints.

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.