Researchers from MIT and Microsoft have developed Murakkab, a system designed to optimize the creation and deployment of AI agentic workflows. Murakkab automatically selects the most suitable AI models and tools, configures necessary hardware, and dynamically allocates computational resources. Initial tests demonstrated significant improvements, including a 65% reduction in computational units, a 73% decrease in energy consumption, and over a 75% cost saving, all while preserving performance levels. AI
IMPACT Murakkab's demonstrated cost and energy savings could accelerate the adoption of complex AI agentic workflows in resource-constrained environments.
RANK_REASON The cluster describes a new system developed by academic and industry researchers for optimizing AI agent workflows.
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →