implementation

Optimize Designs with Simulation Feedback & Groq

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

Linked challenge: AI-Driven Supercapacitor Design via Pore Network & Electrolyte Optimization

Format

Text-first

Lines

Sections

Linked challenge

AI-Driven Supercapacitor Design via Pore Network & Electrolyte Optimization

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Establish an iterative optimization loop where proposed designs from Claude 3.5 Haiku (via DSPy) are evaluated by your `PoreNetworkSimulator`. The simulation results (charging time, capacitance proxy) should then feed back into DSPy, which refines its prompts to Claude for subsequent design iterations. Ensure that Groq is utilized for rapid inference whenever Claude 3.5 Haiku is called, allowing for quicker exploration of the design space. Aim to identify a set of Pareto-optimal designs.

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

AI-Driven Supercapacitor Design via Pore Network & Electrolyte Optimization

This challenge focuses on leveraging AI to accelerate the design of next-generation supercapacitors. Participants will develop a computational framework that intelligently explores and optimizes pore network architectures within electrode materials and proposes compatible electrolyte compositions to achieve superior charging speeds and energy densities. The emphasis is on building a robust design pipeline capable of integrating material property prediction with transport simulations. The solution will use advanced physics-informed machine learning techniques to predict key performance indicators (KPIs) from material structure and composition, thereby reducing the need for exhaustive experimental trials. By simulating tortuosity and ionic transport within complex pore geometries, developers will identify optimal material designs for faster ion diffusion and higher surface area utilization, driving innovation in energy storage materials and manufacturing.

Open challenge

Related prompts

Browse library

Model Pore Network & Ion Transport

planning

AI-Driven Design Proposal with Claude 3.5 Haiku

implementation

Performance Analysis & Design Recommendation

testing