Phase 4: Multimodal Deployment · ~240 minutes · Python
Multimodal Agents and Computer-Use (Capstone)
The 2026 frontier product is a multimodal agent that reads screenshots, clicks buttons, navigates web UIs, fills forms, and completes workflows end-to-end. SeeClick and CogAgent (2024) proved the GUI-grounding primitive. Ferret-UI added mobile. ChartAgent introduced visual tool-use for charts. VisualWebArena and AgentVista (2026) are the benchmarks the frontier chases — and even Gemini 3 Pro and Claude Opus 4.7 score ~30% on AgentVista's hard tasks. This capstone pulls together every thread of Phase 12: perception (high-res VLM), reasoning (LLM with tool use), grounding (coordinate output), long-horizon memory, and evaluation.
What you will learn
- Design a multimodal agent loop: perceive → reason → act → observe → repeat.
- Build a GUI grounding output schema (click coordinates, type text, scroll, drag) the VLM can emit as JSON.
- Compare screenshot-only agents vs accessibility-tree agents vs hybrid agents.
- Set up a multimodal agent benchmark evaluation on a small VisualWebArena slice.
Introduction
- Type: Capstone
- Languages: Python (stdlib, action schema + agent loop skeleton)
- Prerequisites: LLaVA and Visual Instruction Tuning, Qwen-VL Family and Dynamic-FPS Video, the Agentic AI Engineering course
- Time: ~240 minutes
Objective
Learning objectives
- Design a multimodal agent loop: perceive → reason → act → observe → repeat.
- Build a GUI grounding output schema (click coordinates, type text, scroll, drag) the VLM can emit as JSON.
- Compare screenshot-only agents vs accessibility-tree agents vs hybrid agents.
- Set up a multimodal agent benchmark evaluation on a small VisualWebArena slice.
Unlock the full lesson
You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.
Create a free account — the opening phases of 29 of 35 courses are free, no credit card.
Browse all courses · View pricing · DeVenture Academy