What is beneficial friction?
A working definition from MIT Sloan
beneficial friction (noun)
Cognitive and procedural speed bumps intentionally added to workflows to promote more responsible and successful use of generative AI.
Reducing friction is often seen as a business goal, given that frictionless processes and transactions are generally easier for customers and employees alike.
But sometimes friction is a good thing, according to MIT Sloan senior lecturer and research scientist Renée Richardson Gosline. When it comes to using artificial intelligence, humans tend to “anchor,” or fixate, on AI-generated content, even if they know there’s a possibility of error. Adding a little bit of friction can help promote more responsible and successful AI use by prompting users to pause and think more deliberately.
Working with a team at Accenture, Gosline looked at employees’ behavior when completing a writing task using a tool that highlighted potential errors or omissions in AI-generated content. Adding a medium level of friction pushed users to scrutinize the generated text without being a significant drag on the time it took them to complete the task.
These types of “speed bumps” can help workers avoid fast, unconscious decision-making in situations when slower, more deliberative thinking is warranted. “We want to use models to shave time off work, but we don’t want to leave users open to risk,” Gosline said.
To help improve the accuracy of generative AI, add speed bumps | MIT Sloan
Working Definitions: Artificial Intelligence
MIT Sloan's Working Definitions explore the words and phrases behind emerging management ideas.
Leading the AI-Driven Organization
In person at MIT Sloan
Register Now
How to shape platform strategy for humans and AI agents
Design, governance, and data decisions need rethinking as AI agents join platforms as participants, according to MIT Sloan School of Management professors Pierre Azoulay and John Horton.
4 MIT Sloan startups to watch in 2026
The 2026 MIT delta v Demo Day showcased startup innovations from the MIT Sloan community.
What effective AI leaders already know
Implementing AI agents at scale requires leaders to deeply understand the technology, invest in domain experts, and learn how to manage agents along with people.
Scale makes firms’ automation efforts worth the investment
Whether a task is worth automating depends not only on whether machines are cheaper than human labor but also on whether the task is performed at scale to spread fixed costs.
4 areas where companies need AI guardrails
To avoid redundant investments, applications that don’t scale, and unexpected costs and risks associated with AI, organizations should determine where oversight is likely to have the greatest impact.
Increase your personal productivity in an AI-enabled workspace
To gain maximum productivity from AI, MIT Sloan’s Robert Pozen advises senior leaders to use AI as a co-worker, focus AI on the final product, and delegate work to AI without abandoning judgment.
The 5 forces creating urgency around ethical AI adoption
In his book “Boundaries of Tolerance,” MIT Sloan School of Management senior lecturer Jeffrey Saviano argues that ethical AI strategy and governance are the defining leadership challenges of our time.
Stop debating automation vs. augmentation
As organizations begin deploying agentic systems that can execute entire workflows, a consequential question is emerging: How can leaders turn agentic AI productivity gains into business growth?
How to level up systematic innovation with AI
Artificial intelligence can boost the systematic innovation of products, processes, and services. MIT Sloan professor Steven Eppinger offers four steps for making that happen.
AI and jobs: 4 takeaways from Google’s chief economist
Google’s Fabien Curto Millet examined how AI is reshaping job roles, workflows, and employee training in an address at the MIT Stone Center on Inequality and Shaping the Future of Work.