Read position, not a single stock number
On-hand, reserved, and inbound separately. Treating reserved as available is how you advertise a SKU you already promised.
Inventory
What to reorder today, what is about to stock out, and what has quietly become dead stock — from live position, lead times, and open POs. Not an unattended purchaser.
Last updated: August 31, 2026
Buyers still rebuild "what needs a PO" from a spreadsheet, last month's velocity, and a promo calendar in someone's head. Auto-send is worse: a flash-sale day becomes the run rate, reserved units look like a stock-out, and you stack a PO on inbound that lands next week. A reorder-point formula that already posts the right qty does not need an agent wrapped around it.
An inventory agent ranks SKUs as reorder, wait, stock-out risk, or excess from on-hand, reserved, inbound, lead time, and open POs. It drafts a purchase order. A named buyer sends it. Demand forecasting and PO construction are part of this family. Merchandising and margin sit here as a section — not a sixth top-level SKU.
Workflow
Reads, tools, then a stop. Skip the stop and you have a demo.
On-hand, reserved, and inbound separately. Treating reserved as available is how you advertise a SKU you already promised.
Velocity, lead time, open POs, and the promo calendar you can actually attach. Rank reorder vs wait vs excess.
Vendor, qty, and the evidence the buyer needs. The agent does not submit the order.
A human with buying authority approves. Tokens that are not buyer or admin cannot create a purchase order.
Systems
Named tools only. Anything undeclared is unreachable, regardless of the prompt.
Live position with as-of timestamps. A nightly dump without as-of is how the brief lies after 10 a.m.
Preferred vendor, lead time, and open POs so the agent does not stack a second order on inbound.
Sales velocity and any forecast you trust enough to put behind a named tool — not a model guessing from the PDP.
Every purchase order is a proposal. Cedar should deny createPurchaseOrder for any token that is not a buyer or admin. If you cannot name the person who must approve every PO, do not build this agent yet.
What good looks like
Qualitative on purpose. We do not have published agent case studies, so we will not invent a percentage.
Buyers see reorder / wait / excess with evidence. The formula you already trust can keep posting; the agent covers the cases the formula cannot see.
The brief fails if it collapses position into one "stock" number. That is a product rule, not a hope.
Dead stock and giveaway pricing show up here as a section and a linked guide — not a separate commercial family in v1.
This page is the commercial summary for an inventory agent. Reorder ranking, purchase-order drafts, and demand inputs each have a field-guide post. Those posts keep their canonicals. This page tells you what we sell and what we will not automate unsupervised.
Which SKUs are quietly destroying margin, and which need a merchandising pass, is the same live inventory and price picture. We did not add /ai-agents/merchandising/. Read the margin intelligence guide, then come back here or to operations if the pain is the morning triage rather than the buy.
There is no native Shopify AgentCore inventory connector. Shopify, Magento, and custom stacks look the same at the tool boundary — we attach to your WMS or admin APIs.
Name the buyer. Expose on-hand / reserved / inbound as separate fields. Then the eCommerce AI Agents engagement. If join keys across SKU, warehouse, and open PO are fiction, start with the knowledge agent.
These posts are the long-form canonicals. This page does not replace them, and they are not redirected here.
AI Inventory Agent: What Should We Reorder Today? (2026)
An AI inventory agent ranks SKUs as reorder, wait, stockout risk, or excess — a risk brief, not an auto-PO. Reuse Gateway ~180→95 ms and ~$791/mo at 50K, not a client turns-of-cover KPI.
AI Purchase Order Agent for eCommerce (2026)
An AI purchase order agent drafts qty, vendor, and need-by from inventory risk and demand — a human still sends the PO. Reuse Gateway ~180→95 ms and ~$791/mo at 50K, not a client buying KPI.
AI Demand Forecasting Agent for eCommerce (2026)
An AI demand forecasting agent explains the number a stats model already owns — likely demand, why, and what to do. Reuse Gateway ~180→95 ms and ~$791/mo at 50K, not a MAPE claim.
AI Margin Intelligence Agent: Which eCommerce Products Are Actually Profitable? (2026)
Revenue is not profit. Rank SKUs only when cost, discounts, shipping, returns, ads, and fees exist — else unknown. Reuse Gateway ~180→95 ms and ~$791/mo at 50K sessions.
AI Agent vs Workflow Automation: What Should eCommerce Businesses Use? (2026)
AI agents do not replace Shopify Flow or OMS state machines. Hybrid is the default: rules own money movement; the agent returns a structured decision. Reuse Gateway ~180 to 95 ms and ~$791/mo at 50K sessions — not store conversion KPIs.
Human-in-the-Loop AI Agents for eCommerce: Where Automation Should Stop (2026)
HITL is a queue with session id and tool trace — not a prompt. Reuse Gateway ~180 to 95 ms and ~$791/mo at 50K sessions. Do not auto-approve on SLA timeout.
The eCommerce AI Agent Readiness Assessment: Is Your Business Ready? (2026)
Score org-wide AI agent readiness /30 — data, integration, process, governance, priority. Below 16, skip writes. Reuse Gateway ~180→95 ms and ~$791/mo at 50K sessions.
eCommerce AI Agents on AWS
Production AI agents for eCommerce on Amazon Bedrock AgentCore — support and WISMO, inventory, merchandising, margin, returns and B2B. Tool boundaries, evals before launch, and a human on anything that moves money.
Agentic Commerce Readiness
Make your store sellable to AI shopping agents. ACP and UCP protocol surfaces, an MCP server over your catalog, and product data that survives an agent comparison — built on AWS.
Family page → industry or decide tree → the engagement. AWS cases on this site are not agent results.
Other families
The same WISMO, tracking, and returns questions every day. An agent looks up the order, answers from live data, and hands off the moment it is out of its depth.
Quote requests, reorders, and account questions from buyers who will not tolerate a chatbot. An agent drafts the next step; a human still owns the relationship.
The morning pile: exceptions, stalled orders, and the work nobody wants to triage. An agent ranks what needs a human today — it does not silently rewrite the warehouse.
If orders, customers, products, and inventory cannot be joined, an agent will guess. This is the data layer that makes every other agent honest.
Common questions
Tell us how POs get made today. If you cannot name the buyer who must approve every one, we will stop there.