ShelfSentra
Connect in-aisle shelf checks with tasks for store teams. Evaluate stockout alerts and recovery time against staff-checked observations.
Capabilities
- Out-of-stock and planogram variance detection
- Tasking API and handheld-device workflow
- Shelf recovery measurement and reporting
From shelf observation to a staff task
ShelfSentra connects in-aisle camera observations with out-of-stock and planogram checks, then sends tasks to store devices. Define the shelves, SKUs and current planogram before evaluating detections. A changed display, an obstructed camera or an outdated reference can change what an alert means.
Inputs and outputs
- Inputs to agree
- Use representative shelf views, product identifiers and the applicable planogram version. Include the store, aisle and shelf identifiers needed to locate an observation.
- Outputs to review
- Agree what evidence accompanies each task, who receives it, and how staff confirm a correction or reject a false alert. Define the events used to measure recovery, such as task creation and staff-confirmed correction.
Integration and operating limits
Scope the tasking API and handheld workflow against the store's actual systems. Confirm identifiers, task ownership, offline behavior and completion reporting before connecting other inventory or reporting systems.
A view outside the agreed coverage is not proof that a product is available. Separate unreadable or obstructed observations from scored detections. Review camera placement, access and retention with the store team.
What to measure
- Missed stockouts and false alerts against staff-checked observations
- Time from a defined task event to confirmed shelf recovery
- Coverage gaps, rejected tasks and unresolved exceptions by shelf or category
A small shelf-check example
These four records are invented to show an acceptance check. Each observation checks one SKU across all its assigned facings in a defined shelf area, with all required reference views assessable. They are not camera detections produced by ShelfSentra or results from a store.
Scroll the table sideways to read every column.
| Shelf check | Staff observation | Candidate result | Expected evaluation label |
|---|---|---|---|
| A | Checked SKU absent | Stockout alert | Correct alert |
| B | Checked SKU present | Stockout alert | False alert |
| C | Checked SKU absent | No stockout alert | Missed stockout |
| D | Checked SKU present | No stockout alert | Correct absence of alert |
This sample contains two staff-confirmed stockouts within the defined shelf area, but only one was flagged. It also contains two alerts, one of which was false. Counting alerts alone would hide both problems.
The four labels are one correct alert, one false alert, one missed stockout and one correct absence of an alert. Four observations illustrate the labels; they do not estimate store-wide performance.
Define each check by SKU, shelf area, observation time and applicable planogram. Staff check all assigned facings for that SKU in the defined shelf area, and all required reference views must be assessable. An empty facing alone does not establish absence when another assigned facing contains the SKU. Keep an obstructed view in a separate unassessable category rather than counting it as a correct detection or proof of availability.
If recovery time is measured in a real evaluation, define its start and end events, such as task creation and staff-confirmed correction. That interval is not automatically the full duration of the stockout.
Download the synthetic worksheet (JSON)Industry context
Explore the related workflows and other solutions for your industry.