Multimodal Prompting with Agents

A live session on multimodal prompting for agents, based on the article What Comes After the Prompt. What we will cover: The task workflow, a bigger unit of prompting that bundles a long voice note, the current screen, annotations, and exact text into a single turn Real examples of one-pass handoffs and how richer context cuts down correction loops How stored task traces turn into reusable skills for future agents A live demo of multimodal prompting inside our own agent orchestrator Practical tips for applying this to browser use, computer use, and parallel agent workflows Free and open to everyone.