AWS · MLA-C02 · BETA
Agents in production
MLA-C02 · Lesson 15 of 23 · 2:00:18
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Lesson 15 of the free MLA-C02 beta series (AWS Certified Machine Learning Engineer – Associate, domain 3, deployment and orchestration). In this lesson: AgentCore Runtime and its sessions, tools, MCP, A2A, Gateway, Identity, and Policy, state and memory, and versions, endpoints, and deployment pipelines for agents. With three quick checks and a recap, and AnyCompany Mobility, a car sharing service, as the running example.
Preview the topics
- The booking system has a REST API with an OpenAPI description, and two Lambda functions handle damage claims. Several agents must use them as MCP tools, through one secure endpoint, with little new code. What should the ML engineer use?
- A customer chats with the agent today, and comes back next week. The agent should still know the preferred car type and language, without asking again. What should the ML engineer use?
- Developers change the agent many times a day, but production must stay on the version that passed last week's tests, until the next release. How should the ML engineer configure the endpoints?