AI Studio

From AI Agents to the Agentic Web

A hands-on MIT course for building AI agents and the systems they need to act across the digital and physical world.

Applications are reviewed in waves. Apply early for priority consideration.

MAS.665 / MAS.664 / EC.731 / IDS.865



Overview

Learn to build working agentic systems and understand how agents will change software, organizations, services, and everyday work.

At a Glance

Class: Thursdays, 10:00 AM–12:00 PM, starting September 10, 2026

Location: MIT Media Lab, E14-633

Format: lectures, discussion, practical assignments, and individual or small-team projects

Commitment: approximately 6–10 hours per week outside class

Who Should Apply

Students who want to build useful systems with AI and understand where agentic technology is going.

Strong applicants may bring experience from engineering, product, research, design, business, or other fields.

Everyone is expected to build with modern AI tools and agents, learn through experimentation, and contribute to working projects.

MIT students and eligible cross-registrants are welcome to apply.

What You Will Learn and Build

The course connects each topic to the Agentic Web: an ecosystem in which agents discover tools, exchange information, use services, and act for people and organizations.

Personal Agents

Build agents for research, coding, planning, learning, or repeated work using context, memory, personal data, and tools.

Agent Loops and Autonomous Work

Design agents that plan, act, evaluate results, recover from failure, and know when to ask a person for help.

Multi-Agent Systems and Organizations

Coordinate specialized agents through delegation, task routing, shared memory, communication, and review.

Products and Infrastructure for Agents

Build APIs, tools, services, and environments that agents can discover, use, and combine across the web.

Open and Local Models

Explore model choice, local inference, adaptation, privacy, latency, deployment, and cost-quality trade-offs.

Robotics, Embodied Agents, and World Models

Connect multimodal perception, simulation, spatial reasoning, planning, and action across physical and online environments.

The Agentic Web

Study identity, delegated authority, permissions, trust, payments, shared protocols, security, and agent-to-agent communication.

Applied Topics

Apply agentic systems to emerging forms of economic activity, organizational work, and collective decision-making.

Agentic Commerce

Explore markets where agents discover services, compare offers, negotiate, transact, and build reputation on behalf of people and organizations.

Agentic Organizations and Work

Design teams of agents that operate workflows, share knowledge, allocate tasks, and coordinate decisions with people.

Agentic Societies

Study identity, trust, governance, voting, norms, privacy, and dispute resolution when autonomous agents participate in collective systems.

Course sandbox: NANDA Town. Students will use this open Project NANDA environment to create scenarios where agents talk, trade, vote, and team up; test protocols before deployment; and analyze how agent interactions succeed or fail.
Course format: Weekly classes combine instruction and discussion with regular building and testing. Students complete practical assignments and develop a final project with checkpoints, mentor feedback, and a Demo Day.

How to Apply

The application has two required steps. Applications are reviewed in waves, and earlier applications receive priority.

Application Steps

  1. Complete the Fall 2026 Questionnaire (Step 1).
  2. Complete the Fall 2026 Build Assessment (Step 2) by building and submitting a small working application that uses AI to complete a useful task.
  3. Complete any additional registration forms required by MIT or Harvard.

Application Waves

  • First wave: apply by August 1, 2026.
  • Second wave: apply by August 15, 2026.
  • Final wave: apply by September 1, 2026.
  • Late applications: a few seats may be available after September 1, but admission is not guaranteed.

How Applications Are Reviewed

We assess readiness to build, relevant experience, interest in the course, and expected contribution to a team.

In each wave, applicants may be accepted, rejected, or waitlisted. Earlier waves receive preference, so apply early if possible.

Admission is selective, and completing the application does not guarantee a place in the course.

Before You Submit

Complete both application steps; Step 1 alone is not a complete application.

Use the same full name and email address in both forms. If you have an MIT ID, use your primary MIT email and official MIT name.

MIT registration or Canvas access does not replace the course application.

Course Schedule

The detailed weekly calendar is TBA and will be posted once the semester calendar is finalized.

Class Meetings and Key Dates

  • Weekly class: Thursdays, 10:00 AM–12:00 PM, in E14-633 at the MIT Media Lab.
  • Pre-course information session and social: late August or early September 2026; details will be announced in advance.
  • First class: Thursday, September 10, 2026.
  • Final demo materials due: Thursday, November 19, 2026.
  • Final presentations and Demo Day: Thursday, December 3, 2026.

Additional Information

Assignment deadlines and project milestones will be published on Canvas.

Workshop, mentor, and guest speaker dates will be announced in advance throughout the semester.

The course may count toward the Entrepreneurship and Innovation Minor. Contact eiminor_admin@mit.edu to confirm eligibility and requirements.

Projects and Demo Day

Fall 2026 projects will contribute to the emerging Agentic Web: software that AI agents can use to complete tasks and interact with other agents and services.

Final Project

A working minimum viable product (MVP), such as an infrastructure component, product, service, or shared standard.

A clear way for agents to interact with it, such as a tool interface or environment where the agent runs.

Documentation showing how an agent uses it, plus evidence that it works in realistic scenarios.

Support and Demo Day

Each team works with a mentor and receives access to technical workshops and support sessions.

Final projects are presented at Demo Day on December 3, 2026.

Each team will give a focused 2–3 minute live demonstration.

View detailed project and Demo Day requirements
  • Projects may include infrastructure components, agent-ready products, services, environments for agents, and security or reliability tools.
  • Each project should solve a clear problem, explain what an AI agent can do with it, and integrate with relevant agents, infrastructure, or services.
  • Possible focus areas include identity, reputation, permissions, payments, memory, monitoring, evaluation, adversarial testing, service marketplaces, and workflow automation.
  • By November 19, each team must submit its final title, team list, project URL, presentation deck, and any table or booth needs.
  • Teams should plan for three mentor meetings and arrive with specific questions, a working artifact, and clear next steps.

Course Instructors

Course TA

Course Team

Mentors and Guest Speakers

Fall 2026 mentors and speakers will be announced throughout the semester. Sessions will emphasize working systems, implementation choices, failures, deployment, reliability, and lessons from practice.

FAQ

What backgrounds are a good fit?

Students join from engineering, product, research, design, business, and other backgrounds. Everyone is expected to build with modern AI tools and agents, contribute to working projects, and learn through experimentation.

What is the Agentic Web?

The Agentic Web is an ecosystem of connected AI agents, tools, services, and shared standards. Agents can discover services, exchange information, and combine tools to complete tasks across different systems.

Is collaboration allowed?

Yes. Peer groups and mentor feedback are part of the course. Students should help each other learn while submitting their own work and documenting team contributions clearly.

Do I need a startup idea?

No. The course focuses on learning and building agentic systems. Projects may become products or ventures, but they may also be research tools, open-source infrastructure, personal agents, or public-interest systems.