Software Defined Talk Episode 558: Tara Raj on Amazon Nova Act
Feb 6, 2026
Tara Raj, Senior Engineering Manager at the Amazon AGI Lab who previously worked on WSL and VS Code, discusses agent-based automation and Nova Act. She explains how Nova Act automates browser workflows from a single natural-language prompt. Conversation covers using the SDK and playground, deploying runtimes, training with screenshots and safe gyms, and practical normcore agent use-cases like QA and web data tasks.
AI Snips
Chapters
Books
Transcript
Episode notes
Agents As Trusted Business Teammates
- Amazon AGI Lab aims to build AI agents as trusted teammates for business-critical work, not just demos.
- Nova Act focuses on reliable browser agents that automate repeat, mundane tasks for real productivity gains.
Model Plus SDK For Natural Workflows
- Nova Act combines a model plus an SDK to let users express browser workflows in natural language.
- Developers get both simplicity (one sentence prompts) and optional deeper control via Python.
Run Agents In AgentCore Runtime
- Deploy agent workflows as containerized Python code to AgentCore runtime for scale and per-request isolation.
- Treat runtime triggers like AWS Lambda functions and integrate with normal AWS tooling.
