AWS Cloud Architect & AI Expert
Run ten real lookups and three must-escalate cases before anyone outside the team sees the agent. Under 16 out of 30 on readiness, do not add a write. We are not publishing a pass rate from a client store.
Quote the customer's contract price, or say you cannot. A $5,000 auto-issue figure in the field guide is a placeholder, not your cap. A person still sends the quote. The public catalog is not the contract.
Ask for a risk brief, not a purchase order. A sample SKU at 5 days of cover is a fixture, not a client result. A buyer still sends the PO. Auto-send is an unattended purchaser.
Checked 11 Oct 2026: Jev 1.13.0 is still $0.042/MTok, now published at 80 requests/s and 100,000 tokens/s. On AWS it remains an external System-1 sidecar next to Amazon Bedrock, not a Bedrock model.
On Sep 18, 2026 AgentCore microVM Runtime V2 went GA. AWS P75 cold starts were 1.9 to 2.0s vs 5.4 to 30s on V1, but consumption rates rose to $0.1276/vCPU-hour and $0.0169/GB-hour. Memory reclaim waits 120 seconds.
A chatbot searches help articles. An agent uses tools and can be stopped. Relabeling search as an agent is how Browser-hot pilots hit ~3× Runtime-shaped spend.
Take the lookup work off the queue. Where-is-my-order is about 18% of tickets. Refunds stay with a person. We are not publishing a tickets-down percentage.
Score volume, pain, data, and write-risk. Readiness below 16 out of 30 means do not fund writes. McKinsey found 62% experimenting and 23% scaling in at least one function.
Automate the lookup pile first, not tax, capture, or labels. McKinsey found 62% experimenting with agents and 23% scaling in at least one function.
Start with readiness out of 30, then one family, usually support reads. Below 16 out of 30, do not let it change orders. McKinsey found 62% experimenting and 23% scaling.
Your copilot and a third-party shopping agent should read the same facts as add-to-cart. Baymard still puts cart abandonment at 70.22%. Agent-ready is structured data, live ATP, checkout-true price, and APIs, not autopilot checkout.
On Monday the AM desk gets an agent that caps accounts requiring attention at 5 rows with evidence on each. Sales still owns the call. Demo dollars are fixtures.
Our articles share what we know. Our consulting engagements apply that knowledge to your specific AWS environment.
