Thousands of small decisions on price, stock and staffing are made store by store, with little coordination. Head office gets prioritised actions: where to mark down, where to rebalance stock, and which stores need a different roster.
A worked example for a typical Malaysian National Convenience Chain, not a description of any real company. Go through the six stages in order: paste each prompt into Claude, check the answer against how your business really works, then continue. Change the profile at the start to match yours.
Stage 1 of 6
Map how the operation really runs
Act as an operations consultant. I run a National Convenience Chain in Malaysia. Profile: A Malaysian convenience chain — ~1,200 stores, 24-hour operations in urban areas, fresh food, groceries and a growing loyalty programme.
Interview me, one question at a time, to map how decisions actually get made today. Cover: the recurring meetings and reports, who decides what, which numbers people trust, and where decisions are late or made on gut feel.
Known friction: Margin vs. Footfall; Full shelves vs. Waste; Wages vs. Shopper service; One range vs. Local tastes; Opening stores vs. Existing ones.
After 8 to 10 questions, summarise the five decisions that cost us the most when made late, in a table: decision, current owner, current delay, cost of delay.
Stage 2 of 6
Design the specialist agents
Using the decision map above, design 5 specialist AI agents for our National Convenience Chain: Markdown, Replenishment, Store Hours, Store Upkeep, Store Tier.
For each agent give: the one question it answers every day, the data it reads, what it may recommend, what it must never do alone, and the format of its output.
Starting points for what each should watch:
- Markdown: price elasticity, competitor checks, promo performance, markdown timing
- Replenishment: stock-outs, fresh-food wastage, supplier lead times
- Store Hours: labour hours vs. footfall, absence, night-shift coverage
- Store Upkeep: chiller and equipment health, energy use, maintenance tickets
- Store Tier: store tier performance, new-site and closure cases
Keep every agent narrow. If an agent covers two jobs, split it.
Stage 3 of 6
Wire up data and compliance
For the agents above, list the data feeds needed. Likely systems: POS and loyalty data; Supply-chain and DC systems; Store roster app; Facilities and energy meters.
Output a table per agent: field, source, how often it refreshes, data-quality risk, and what the agent should do if the feed is stale or missing. Mark every personal-data field and say how to minimise it.
Rules we operate under: Price-control and pricing-display rules, food-safety and labelling rules, PDPA 2010 for loyalty data, and labour law.
End with a short list of actions that always need human sign-off.
Stage 4 of 6
Design the morning brief
Design the single daily brief that pulls the 5 agents together for the CEO, ready before the first meeting of the day.
Specify how the brief merges overlapping or conflicting recommendations, how it ranks items (impact, urgency, reversibility, confidence), and the exact fields per item: what to decide, recommended action, evidence, owner, deadline, and the cost of doing nothing.
Then write a realistic sample brief of five items. Items might resemble: Mark down the sandwich range after 8pm in 90 stores to cut wastage / Reroute chilled stock to the stores with chiller failures / Reduce night-shift hours at 40 low-footfall stores.
Stage 5 of 6
Build and automate it
Turn the design into a working automation for our National Convenience Chain.
Needs: a scheduled daily run; the 5 agents run in parallel and each saves structured JSON; a final step reads them all and sends the brief by email or chat; every run is logged with inputs, outputs and cost.
Propose the build with Claude plus a workflow tool (for example n8n or the Claude Agent SDK). Give the steps in order, what happens when a data feed fails, and a human-approval step before anything that spends money or makes a customer commitment.
Stage 6 of 6
Roll out and measure
Write a rollout plan for the National Convenience Chain agent team that starts small and earns trust.
Stage 1: one agent, advisory only, run alongside the current process. Stage 2: add the other agents. Stage 3: switch on the daily brief. Stage 4: let agents prepare low-risk actions for approval.
For each stage give duration, owners, what "ready to move on" means, and the metrics to track: time to decision, how often recommendations are accepted, hours saved, and errors caught. Close with the three biggest risks and how we contain them.
