amazon-bedrock

Monday, the account calendar. A ~30-day cadence that goes quiet is an AM task — not a "we miss you" email. Day 38 is a queue row. Sales still decides who speaks.

Vitamins due next week — unless they already subscribe. Predict the window, draft one reminder, never charge the card. Cart abandonment is 70.22%; that is not a refill rate.

The serial-returner spreadsheet becomes "you are fraudulent" in a ticket. Risk bands stay internal. High freezes auto-refund. A person still owns the accusation. The ~$791/mo platform cost floor at 50,000 sessions is planning cost, not fraud recovered.

Finance asks why revenue dropped last week. Someone answers with a TikTok story and no tools. Hop table with evidence per step — Baymard 70.22% is industry context, not your diagnosis.

Monday, the wholesale counter. An agent looks up their net, not the public product page. 3 signed-in roles keep the price book closed. No payment capture.

Shoppers click through from ChatGPT and Perplexity. Adobe measured July 2026 AI-referral traffic to U.S. retail +62% YoY. Instrument that channel before you buy a GEO rank.

Baymard still measures average cart abandonment at 70.22%. A shopping agent that quotes yesterday's stock makes that worse. Score 13 checks before you invite a copilot.

For the person who will build your first store agent on AWS — not a Shopify plug-in. One lookup workflow this week; refunds wait for a person. Planning silhouette ~$791/mo at 50K sessions.

Autonomy is per action, not one store-wide dial. The public worksheet uses a $75 refund ceiling — yours belongs in Policy, not a prompt. Delay notices can go fully automated when the template is fixed.

Five program levels from FAQ assistant to multi-agent ops. Level 5 is optional. McKinsey found only 23% scaling in at least one function.

Score org-wide readiness out of 30. Below 16 out of 30, do not let it change orders. McKinsey found 62% experimenting and 23% scaling — still a minority per function.

Most store AI failures are IDs, APIs, ownership, and evals — not the model. Plan against a published ~$791/mo platform floor at 50K sessions — that is cost, not savings. Run the pre-model gate first.