Insights & Resources

A support agent takes lookup work — WISMO is about 18% of tickets — not auto-refunds. Reuse Gateway ~180 ms → ~95 ms and the published ~3× Browser-hot spend; no ticket-cut KPI.

Score volume × pain × data × write-risk. Treat ~$791/mo at 50K sessions as a platform floor — not store savings. Readiness below 16/30 means do not fund writes.

Automate the lookup pile first — not tax, capture, or labels. McKinsey found 62% experimenting with agents and 23% scaling; reuse the published ~$791/mo AgentCore floor at 50K sessions.

Start with readiness /30 — below 16, skip writes — then one family, usually support reads. Reuse Gateway ~180→95 ms and ~$791/mo at 50K sessions; Harness GA was June 17, 2026.

Agent-ready is structured product data, live ATP, checkout-true price, and APIs — not autopilot checkout. Reuse Gateway ~180 to 95 ms and ~$791/mo at 50K sessions. Score 13 checks separately.

An AM agent should cap "accounts requiring attention today" at 5 rows with evidence_tool on each. Reuse Gateway ~180 ms → ~95 ms on the B2B CRM canary — not a book-of-business KPI. Demo table is fixtures.

Adobe Analytics (1T+ visits) put July 2026 AI-referral traffic to U.S. retail +62% YoY. That is a channel, not a copilot. Score merchant readiness for an external agent before you staff another chat widget.

B2B onboarding agents collect docs and draft account setup — they do not setCreditLimit in week one. Reuse Gateway ~180 ms → ~95 ms from the B2B CRM canary. Credit and contract stay HITL.

Score who deserves attention from historical LTV plus churn risk — read-only, no CRM overwrite. Reuse ~$791/mo at 50K sessions and Gateway ~180 ms to ~95 ms, not a client LTV lift.

An AI agent for eCommerce analytics answers with named tools and a time window — five operations in the catalog, not a 40% insight lift and not unrestricted SQL.

Tool-based integration beats Admin API keys in the prompt. No native Shopify connector. Reuse Gateway ~180 to 95 ms and ~$791/mo at 50K sessions — not an integration SLA.