planning

Crew Member Definitions

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

Linked challenge: Digital Twin Process Control for MoS2 FETs using CrewAI and Letta AI

Format

Text-first

Lines

Sections

Linked challenge

Digital Twin Process Control for MoS2 FETs using CrewAI and Letta AI

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Define two CrewAI agents: 1) Fabrication_Engineer (Goal: Maximize Ion current density). 2) Metrology_Specialist (Goal: Identify process drift using historical data). Assign both agents to a Letta AI backend so they can store 'experiment logs' in long-term memory. Use the CrewAI 'Process.sequential' flow.

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

Digital Twin Process Control for MoS2 FETs using CrewAI and Letta AI

Based on recent breakthroughs in gate structuring for bilayer MoS2 field-effect transistors, this challenge requires you to build an autonomous Digital Twin controller. You will use the CrewAI framework to orchestrate a 'Process Engineer' agent and a 'Metrology Specialist' agent. These agents will collaborate to optimize the gate deposition parameters (temperature, pressure, and time) to achieve ultrahigh current density. To manage the complex, stateful nature of microfabrication cycles, you will integrate Letta AI (formerly MemGPT). Letta AI will provide the agents with 'Archival Memory'—allowing them to store and retrieve historical run data, drift patterns, and sensor telemetry. This prevents the agents from repeating failed experiments and allows them to identify long-term degradation in the virtual manufacturing line.

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.