Track 15: Frontier and Advanced, Frontier Agent Engineering
Multimodal Agents: Screens, Documents and Voice in One Loop
Build an agent that reads images and documents and acts on them.
Get notified on YouTube Udemy certificate: coming soon
Course
Browser, Computer-Use & Coding Agents
Udemy: coming soon
Tools
- Gemini API (freemium)
- Qwen-VL (open-source)
Watch first
In this module
- Why Agents Fail in Production, and Service Levels
- Agent Reliability: Retries, Idempotency, Checkpoints
- Multimodal Agents: Screens, Documents and Voice in One Loop
- Knowledge Graphs for Agents: Query and Update Tools
- Durable Long-Running Agents: Resume After a Crash
- RL Fine-Tuning for Agents: GRPO on Tool Use
- Project: Agent With Knowledge-Graph Memory
The course this lesson belongs to