A multimodal AI agent accepts more than one type of input, such as text, images, audio, video, or documents, decides what to do with it, and acts through tools or APIs. The defining feature is action rather than input variety alone.

An assistant responds to what it is asked. An agent plans a sequence of steps, calls tools, keeps context across those steps, and works toward a goal without being prompted at each stage. This course establishes that distinction before building anything.

General-purpose multimodal models are used for image, audio, video, and document handling, accessed through APIs with free-tier access sufficient for the coursework. Model choice is treated as a decision you make rather than a fixed dependency, and readings cover how to compare options on capability and cost.

You need access to a multimodal model, and free tiers cover the coursework. Where a paid API appears in a demonstration, an open-weight alternative that runs in a free notebook environment is noted.

Tool calling is how an agent invokes an external function or API instead of answering from the model alone, for example to search, fetch a record, or run a calculation. The course covers how to define the tool schema, handle failures, and give the model enough context to choose the right tool.

To access course materials, assignments, and earn a Certificate, you'll need to purchase the Certificate experience when you enroll in a course. Eligible learners may also have the option to start with a Free Trial. Some courses may also offer a Full Course, No Certificate option. This lets you access course materials, submit required assessments, and receive a final grade, but you won't be able to earn or purchase a Certificate.

When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.