Agent Speedrun — Elizabeth Fuentes Leone & Sandhya Subramani, AWS
A customer service agent looks up an account, checks an order, and handles a refund.
Proof1 independent outlet
Key points
- The harder part is controlling what happens between those steps and keeping that control when the agent reaches production.
- Elizabeth Fuentes Leone and Sandhya Subramani build the workflow with Strands Agents, starting with a system prompt and three tools backed by mock customer data.
- They inspect messages and tool calls, add a conversational interface, then introduce a hook that limits tool invocations.
- 2:36 - AgentCore runtime and services
Sources (1)
- [1]Agent Speedrun — Elizabeth Fuentes Leone & Sandhya Subramani, AWSAI Engineer (YouTube) · Oct 11, 03:00 PM
A customer service agent looks up an account, checks an order, and handles a refund.
The harder part is controlling what happens between those steps and keeping that control when the agent reaches production.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing
- Oct 7, 2026Beyond hours saved: Building the business case for agentic automation
- Oct 7, 2026Automate remediation post AWS DevOps Agent investigation
- Oct 7, 2026Building AI builders: Playbook for closing the AI knowledge-capability gap
- Oct 7, 2026How Cornerstone OnDemand cut database diagnosis by 78% with Amazon Bedrock