Agentic AI in the Browser: Building Autonomous Web Agents
AI in web applications is often reduced to chat interfaces and prompt-driven interactions. While useful, this represents only a small part of what intelligent systems can do.
In this workshop, we will explore agentic AI in the browser; systems that can observe their environment, make decisions, and take action using modern Web APIs. Participants will build autonomous, goal-driven agents that run entirely in the browser, without relying on server-side execution for core behaviour.
Through hands-on exercises, we will implement an agent loop, run agents inside Web Workers, persist state using IndexedDB, and safely expose browser capabilities such as file access and notifications. We will also focus on guardrails: permission models, explainability, user control, and offline-first operation.
By the end of the workshop, attendees will have a working agent architecture and a set of practical patterns they can apply to real-world web applications and internal tooling.

Lucky is an Executive and the Head of Specialised Consulting, Research and Development at BBD - a global bespoke software solutions firm. As a software engineer, he has experience in building and maintaining enterprise software in the banking, insurance, telecommunications and education sectors with varying tech-stacks; from VB6 and .Net to web and cloud technologies.
Lucky is an educator, teaching Game Design and Computer Science at the University of the Witwatersrand, Johannesburg and is the co-organiser of the Johannesburg-based JavaScript-focused meetup: Jozi.JS.
