Which accounts are slipping — and what to do this morning
Copilot already scans a storefront read-only in 60–90 seconds, writes a daily brief and ranks evidence-backed actions you can apply, measure and revert. Its B2B twin will read the account book as well as the storefront: the accounts that have passed their usual reorder window, the quotes ageing past the point they normally close, and the price-list pages where buyers stall. Same scan, same brief, same reversible actions — pointed at accounts.
- Roadmap product — no date announced
- Read-only scan — never changes your storefront
- Missing inputs shown explicitly, never assumed
Four key accounts have passed their usual reorder window and two quotes are ageing past the point they normally close. Both are reversible actions on accounts you already have.
Based on catalog scan · connected sources only · manual approval
60–90 seconds · nothing was applied to your storefront
Autopilot guardrails
Illustrative roadmap interface — fictional accounts, not a B2B measurement.
60–90 s
Read-only storefront scan
Homepage, catalogue, a sample product page and the cart — read the way a buyer would, nothing applied
70+
CRO score target
A 0–100 score with a six-part weighted breakdown; “Healthy” starts at 70
17
Data sources, each shown live or not
Every source is marked Connected or Unavailable — Copilot only reasons over what is connected
3 / day
Autopilot cap by default
10 per week, minimum 80% confidence, low risk only, reversible only — checkout always blocked
These figures describe Copilot as it ships for Shopify DTC stores today. The account-health brief is on the roadmap — nothing here is a B2B measurement or screenshot.
Every morning: which accounts moved, and which stopped
Copilot writes a daily brief today — at 04:30 UTC and on demand after any scan — from metrics against the previous day and week, top products, orders, behaviour, module status and the CRO snapshot. Its B2B twin will add the account view on top of that: the accounts past their usual reorder rhythm, the quotes older than the store’s own typical decision window, the price-list and spec-sheet pages where buyers arrive and leave. Each line will end in something you can do — a Callio campaign on the column, a chase, or an item in the Action Plan.
- Key figures with “vs prior period” or “No comparison” — never a blank filled with an assumption
- “Do this first”: the highest-impact opportunity with its priority, confidence and modelled potential, then 02, 03, 04 in sequence
- “Signals to verify” — missing inputs are shown explicitly. Copilot will not replace them with assumptions, and account objects it cannot read yet will say so
Comver AI Commerce OS
AI Commerce Copilot
Daily brief · Aug 16, 2026, 06:30
Mobile add-to-cart trails desktop by 4.5 points and the cart drawer hides the free-delivery threshold. Two low-risk, reversible changes cover most of this month’s gap.
Based on storefront scan · 12 store signals · Manual approval
Conversion Rate
2.6%
−0.3 pts vs prior day
Average Order Value
$74
+2.1% vs prior day
Cart Abandonment
68%
+1.4 pts vs prior day
Mobile Sessions
61%
No comparison
Priority 01
88%
confidence
Do this first · Highest-impact opportunity
Add a sticky add-to-cart bar on mobile product pages
Mobile add-to-cart rate 8.9% vs desktop 13.4% (Comver storefront events). Sticky ATC is an inactive Comver module — activate it from Revenue modules.
Connected data sources
14 of 17 connectedHeatmaps · Unavailable — no behaviour events in the comparison window. Copilot will not replace them with assumptions.
The same read-only scan, pointed at the catalog
Run AI scan and Copilot opens your public pages the way a buyer does, then scores what it finds. Four passes — connect, read, score, quantify — then it writes the brief. Nothing is applied to your store. For B2B the same scan will read the pages buyers actually use: the catalog, the price-list and MOQ tables, the spec sheets and the quote form, and score the friction it finds there.
- A CRO score from 0 to 100 with a six-part weighted breakdown, trended across your last six scans against a dashed “Target 70” line
- Top conversion issues with recommended fixes, detected opportunities, missing signals and a directional monthly revenue-leak range — labelled as an estimate
- Read-only: the scan fetches public pages and takes screenshots. If anything fails you see “Nothing was applied to your store.”
What this scan does
Four storefront passes, then your brief
Copilot opens your homepage, a product page and the cart the way a shopper does, then scores what it finds against the same CRO evidence the rest of the dashboard uses.
This usually takes 60–90 seconds. Stay on this page.
Ranked, evidence-backed. Apply, measure, revert.
One queue holds open recommendations and in-flight changes, sorted priority → impact. Prepare change turns a recommendation into an exact, reviewable proposal; every applied change is measured against its own plan and can be reverted in one click. The B2B twin adds account-shaped rows to the same queue.
Every recommendation with its stage, confidence and estimated impact
Filter by priority and status. Each row shows the category, the page or account it touches, confidence and modelled impact (or “Not estimated”), and its stage: Detected, Suggested, Ready to review, Manual required, Approved, Scheduled, Live, Measuring, Completed. Anything not controlled by a Comver module becomes “Manual required” — Copilot never edits your theme behind your back.
Comver AI Commerce OS
AI Commerce Copilot
Sorted priority → impact · Stages: Detected · Suggested · Ready to review · Manual required · Approved · Scheduled · Live · Measuring · Completed · Failed. Anything not controlled by a Comver module becomes “Manual required”.
Ask what changed, why it matters, and who to call
Ask Copilot is a chat grounded in your connected data — Shopify, Comver analytics, modules and audit context — that answers with the numbers and names the source of each one; when a source is unavailable it says so instead of guessing. For accounts the questions change shape: which accounts have gone quiet, which quotes are ageing, where buyers stall between the price list and the quote form.
- Planned account questions: “Which key accounts have not ordered this quarter?” · “Which open quotes are past their usual decision window?” · “Where do buyers drop between the price list and the quote?”
- Answers cite Shopify orders, Comver sessions and events, module config and the latest audit — and mark anything Unavailable rather than estimating it
- The same grounded chat opens from the floating Copilot orb, with prompts that match the page you are on
Comver AI Commerce OS
AI Commerce Copilot
Suggested questions
Grounded in connected data — Copilot names unavailable sources instead of filling gaps with assumptions.
Conversion fell from 2.9% to 2.6% week over week (Shopify orders + Comver sessions). Two things moved:
- Mobile sessions rose to 61% of traffic, and mobile add-to-cart is 8.9% against 13.4% on desktop (Comver storefront events).
- Cart abandonment is 68%, up 1.4 points; 31% of abandoned carts sit $8–15 below the $60 free-delivery threshold, which the drawer does not show (Cart Rewards config).
Heatmaps: Unavailable for this window — no click data was recorded, so I am not attributing the change to a layout cause. The two actions above are already in your queue (01 and 02).
From the first scan to a measured result
No theme edit and no separate app. Copilot lives in the Comver workspace and is reached from the command center, the floating orb and the Action Plan — the B2B twin will be the same surface with account rows in it.
- 1
Connect
Install the Comver Shopify app. Products, orders and customers arrive from the Admin API; switch on storefront tracking and sessions, events, heatmaps and funnels join the connected sources. Companies, buyers and price lists will join from Shopify’s B2B APIs.
- 2
Scan
Run the read-only scan. Sixty to ninety seconds later you have a CRO score, the top issues, a leak range marked as an estimate — and the first brief.
- 3
Decide
Prepare change on any recommendation, review the evidence and the before and after, then Reject, Edit, Schedule, Approve or Apply now. Or let Autopilot handle the low-risk, reversible ones inside your policy.
- 4
Measure
Applied changes move to Measuring. After at least 24 hours and enough sessions on each side, Copilot compares before and after on the plan’s primary metric, records the result and logs it — or you revert.
Estimates say so. Gaps say so.
Copilot keeps facts, estimates and unknowns visibly apart. It never fills a gap with an assumption, never applies a change it cannot roll back, and never touches pricing, checkout, payment, shipping, legal, policy or tracking on its own.
≈
Every money figure is an estimate until measured
Monthly potential, revenue at risk and leak ranges are directional — and say so
0
Assumptions where a source is missing
“Missing inputs are shown explicitly. Copilot will not replace them with assumptions.”
3
Categories locked to manual, always
Checkout flow · speed and technical · pricing and value communication
Copilot executes only on Comver-controlled modules; every other target is prepared for you to carry out. The account-health brief described on this page is a roadmap addition — quote, purchase-order and price-list objects do not exist in the product yet.
Frequently asked questions
No. Copilot ships today for Shopify DTC stores: a read-only storefront scan, a CRO score, a written daily brief and a ranked queue of reversible actions. The account view — slipping accounts, ageing quotes, leaking price-list pages — is on the roadmap and depends on the company, buyer and quote objects that Comver does not model yet.
Nothing. It is read-only: it fetches your public homepage, catalogue, a sample product page and the cart, takes screenshots and scores what a visitor would see. No theme app embed is needed for the scan, the brief or the CRO score, and if anything fails you see “Nothing was applied to your store.”
From your own rows, or not at all. The intention is to derive a reorder rhythm from an account’s own order history and an ageing threshold from how long its quotes usually take to close — and to show “Awaiting data” where there is not enough history, exactly as the product does today for revenue at risk rather than inventing a figure.
Only if you turn Autopilot on, tick the consent checkbox, and only for the categories and risk level you allow — low-risk, reversible changes to Comver-controlled modules above your confidence threshold, within daily and weekly limits. Checkout flow, speed and technical, and pricing and value communication are always manual, and high or critical risk always needs your approval.
Yes. Every applied module change keeps a rollback snapshot, and a snapshot is required before Autopilot may act at all. Revert restores the previous configuration, stops the measurement and logs the revert in the History timeline.
Shopify products, orders and customers; Comver storefront sessions, events, heatmaps, funnels and traffic sources; revenue-module status; the CRO score, revenue leaks and storefront audit. The connected data sources grid shows exactly which of the 17 are live for your store — anything missing is labelled Unavailable, never assumed. Company, price-list and quote sources would be added to that same grid.
Automatically every day at 04:30 UTC for every connected store, and on demand whenever you run a scan. Copilot has no sidebar row of its own: open it from the command center, the floating orb on every page, the command palette or the Action Plan.
All of Copilot. The scan, score, brief, action queue and Autopilot policy run on any Shopify store, including one that sells to businesses. What is missing until AI B2B Commerce arrives is the account model the brief would reason over.
Keep exploring
Get the brief on your storefront today, your accounts next
Run the read-only scan and get your CRO score, brief and first ranked actions in about ninety seconds. Then join the B2B waitlist and help decide what the account-health brief should tell you first.
14-day free trial · Live on Shopify in minutes · Checkout stays in Shopify