Store & Field Operations
Self-checkout loss and shrink detection
Use overhead camera vision at self-checkout to detect non-scans, mis-scans, and ticket switching in real time. Prompts the customer to rescan or alerts a colleague before the transaction completes.
20–40%
reduction in self-checkout shrink
Opportunity assessment
Moderate impact. Meaningful cost or revenue improvement, likely noticeable at function level but modest relative to total business scale.
Moderate effort. Requires configuration, prompt engineering, and testing. A capable team can get there but expect several months.
Moderate data needs. Works with data most businesses hold, but will likely need consolidation, cleaning, or reformatting before use.
High risk. Significant external exposure or regulatory implications. Requires robust oversight and clear accountability.
Moderate people impact. Part of someone's working day changes. Requires training and some adjustment time, but roles remain broadly the same.
Tooling required
Things to consider
A commissioned Forrester Total Economic Impact study of one vendor in this space modelled loss reduction of around $88,000 per store per year, equivalent to 0.14% of revenue, for a composite retailer (Forrester). Treat vendor-commissioned figures as an upper bound and test on your own estate.
The false positive rate is the whole game. A system that challenges honest customers destroys trust faster than shrink destroys margin — set the confidence threshold high and start in alert-a-colleague mode rather than block-the-transaction mode.
Camera placement and lighting drive accuracy more than the model does. Budget for a physical survey of every store, not just a software rollout.
There are data protection implications. Under UK GDPR you need a documented lawful basis, clear signage, a data protection impact assessment, and a retention policy for the footage.
Experiment starter: Instrument two stores with camera vision on four self-checkout lanes each for eight weeks in alert-only mode. Compare their shrink rate against two matched control stores and record how many alerts colleagues judge to be genuine. If genuine-alert precision is below 80%, tune before expanding.
Go deeper in the playbook
Section — Opportunity Identification, including the AI Opportunity Assessment ScorecardSection — Risk and GovernanceThis opportunity scores low on risk exposure — read the risk and governance approach before you start.More in Store & Field Operations
Store task generation and prioritisation
Convert system signals — low stock alerts, delivery arrivals, planogram changes, temperature exceptions — into a single prioritised task list for each store colleague, written in plain language with an estimated duration.
Queue prediction and till opening prompts
Predict checkout queue build-up fifteen to thirty minutes ahead using footfall, basket, and historical patterns, and prompt the duty manager to open tills before the queue forms rather than after.
Field visit report drafting from voice notes
Area managers and field engineers dictate a visit summary on their phone. AI transcribes it, structures it against the standard report template, extracts actions with owners, and files it to the system.
AI Transformation Playbook
Ready to assess your own opportunities?
The playbook gives you the full 150-opportunity directory, scoring tools, and 100+ templates for every stage of an AI transformation programme.