AI Workflow Architect: MCP & Plugins Expert

Weekday AI; United States; Remote; USD 69,000 - 262,000; Part time

Job summary

Weekday AI is seeking experienced AI power users to evaluate and improve how advanced AI systems handle complex, real-world personal workflows using Model Context Protocol (MCP) and AI plugins/connectors. You design prompts, execute multi-step tasks, record your screen, and assess outputs for practicality, personalization, and reasoning.

You will create structured rubrics to measure performance across tasks.

Qualifications

• Based in United States and available for remote contract work.
• Extensive MCP experience and knowledge of AI plugin ecosystems.
• Frequent use of AI plugins/connectors (Google Drive, Expedia, Notion) for productive workflows.
• Long history of using large language models for multi-step planning and decision-making.
• Strong analytical thinking, written communication, and attention to detail.

Responsibilities

• Design realistic prompts reflecting complex real-world personal workflows.
• Execute multi-step tasks using AI while recording your screen.
• Utilize personal AI plugins and connectors throughout workflow execution.
• Assess AI outputs for practicality, personalization, reasoning quality, and usefulness.
• Identify where AI systems misunderstand context, mis-use tools, or produce unrealistic recommendations.
• Write detailed, structured explanations highlighting AI strengths, weaknesses, and improvements.
• Develop and apply comprehensive evaluation rubrics to measure AI performance across tasks.

Skills

MCP

AI plugins

Analytical thinking

Written communication

Attention to detail

Decision making

LLM usage

Rubric design

Tools

Google Drive

Expedia

Notion

Job description

Weekday AI is seeking experienced AI power users to evaluate and improve how advanced AI systems handle complex, real-world personal workflows using Model Context Protocol (MCP) and AI plugins/connectors. You design prompts, execute multi-step tasks, record your screen, and assess outputs for practicality, personalization, and reasoning.

You will create structured rubrics to measure performance across tasks.