Ami Recipe
Tracks recipe variance and waste per outlet, and shows which dishes are eating the margin.
In food service the margin erodes gram by gram, not month by month. The agent compares the recipe against real consumption at each outlet and shows which dishes are eating the profit.
Job in hand — here is what the agent does
You handed it over once, above. From there the agent watches the data, runs when a business event happens, does the part you delegated and brings the rest back with its evidence. This is what it has done — and what is still waiting for you.
Done by the agent — nobody had to ask
- Read the shift close of each outlet
- Compared recipe to real consumption
- Split waste by dish and by shift
- Set dish sales against the prior period
- Ranked dishes by margin erosion
Waiting on you
- Two outlets unusually far off recipefor you to review
- Updating the recipe for three dishesfor you to approve
Which dishes are eating into the margin?
Three dishes consistently run over recipe, and all three sit in the best-selling group.
Flag the dishes off recipe and send it to the outlet managers.
Flagged the recipe variance on each dish and sent it to the manager of the outlet concerned.
Updating the recipe for the three dishes is outside what you delegated — drafted, waiting for your approval.
Why are those two outlets off?
Both drift most on the evening shift, on the same hand-portioned ingredients. I separated the portioning variance from the prep waste.
Audit log · Ami Recipe · delegated by Chain Operations Manager
The figures in this example are illustrative. In production the agent creates no numbers — it reads and reorders what your system already holds.
- Reads inside your permissions
- Acts only where you delegated
- Every action leaves a trace
Where you meet the agent
- Right inside the module screenSuggestions appear beside the document you already have open, not in a separate app.
- Ask Ami in plain wordsType or speak, in the same language you already use across the system.
- Runs by itself when there is workFires on a business event and brings the work to you, instead of waiting for you to remember.
Where the agent gets its data
The agent has no data store of its own, syncs nothing outward and keeps no copy. It reads directly on the permissioned data layer the module already runs on — within the exact rights of whoever called it.
- Data leaves the company
- Permissions get rebuilt a second time — and can drift
- Figures lag behind the sync cycle
- Recipes and portioning norms
- Real ingredient consumption per outlet
- Sales by dish and by shift
And where does the AI model run?
The diagram above is about where the DATA sits; this is about where the MODEL runs — two different things. Routing follows data sensitivity automatically; you do not pick per task.
See the hybrid AI modelAgents in the same group
Other agents on the same data layer — usually switched on together.
- Ami SourcingCompares quotes, scores suppliers on real delivery history and flags prices that break the pattern.
- Ami StockWarns on stock-outs and dead stock, and proposes replenishment by FEFO and per-warehouse minimums.
- Ami DemandForecasts demand from real sales data, balances it against capacity and simulates scenarios before the plan is locked.
- Ami SchedulingProposes a production-order sequence based on the shop floor's real capacity and flags orders about to run late.
- Ami QualityClassifies defects, traces root cause back to operation and shift, and opens a CAPA with the evidence attached.
- Ami MaintenancePredicts failures from run hours and equipment data, and raises the work order before the line stops.
- Ami FleetPredicts servicing from real distance driven and warns when inspection or insurance is about to expire.
- Ami AssortmentCompares stock in each store against that store's real sell-through, proposes transfers and flags slow movers.
- Ami SeasonForecasts yield by growing region and season, and balances processing capacity before the peak arrives.
- Ami ConsumptionForecasts linen, amenity and kitchen consumption from occupancy, and orders ahead of the peak season.
- Ami PharmacyTracks drugs and supplies by lot and expiry, warns on near-expiry stock and proposes transfers between sites.
What this agent does not do
- It grants itself nothing.The agent pre-fills forms and can write to the system — but only within what you delegated; beyond that it stops at a suggestion.
- There is no data shortcut.The agent sees exactly what the calling account may see — no private connection of its own.
- It never acts anonymously.The log records which agent acted, under whose delegation and who approved — accountability stays with people.
How to switch this agent on
- Your company needs to be running the Inventory & Warehousing module — the agent reads that module's own data.
- No separate permission setup: the agent's rights are the rights of whoever calls it.
- Switched on and tuned during rollout, following your existing approval flow.
The exact scope and the order modules are switched on get settled in the demo, against your current setup.
Questions people usually ask
Can the agent change data on its own initiative?+
Not on its own initiative — but it does more than read. The agent pre-fills forms and writes to the system within exactly the scope you delegated to it; anything beyond that stops at a suggestion and waits for someone with authority. Either route, every action lands in the audit log.
What if the agent suggests the wrong thing?+
Every suggestion carries its evidence: which document, which line, and why. The reviewer edits or rejects it before anything is written — and both of those actions leave an audit trail too.
How is this different from a chatbot?+
A chatbot only answers when asked. An agent also takes a job you hand over once, then watches the data on its own, runs when a business event fires, and reports back — that is the half a chatbot never does.
How is this different from an automation flow?+
An automation flow runs the steps it was configured with. An agent reads business data, ranks it by situation and picks what needs doing — within exactly the scope you delegated, and anything needing approval still goes through your existing approver.
Does data leave the company?+
Tasks that touch sensitive data run on Internal AI placed inside your own infrastructure; only non-sensitive tasks use an external model. Routing follows the sensitivity of the data automatically.
See the agents run on your own data.
Book a demo scoped to the modules and industry you actually need.