Describe constraints in plain language
By Nathan ColeUpdated
The assistant translates requirements stated in your own words into the specific fields the optimizer reads. "The reefer van cannot do the bakery run before 6am" and "leave two low-value drops for tomorrow rather than pay a second driver four hours of overtime" both map onto fields this way. This page walks one prompt through the mapping, shows prompts that state the outcome rather than a setting, and covers comparison runs.
The prompts below work the same in the assistant in the app and in a connected assistant. Both write the same fields through the same tools.
The translation, in one example
The prompt:
Plan tomorrow's 62 deliveries. Two vans, both from the Mons depot,
drivers start at 7:00 and I do not want anyone finishing after 16:30.
The four pharmacy orders have to arrive before 11:00. Chilled orders
can only go on the van with the fridge. If it does not all fit, drop
the lowest-value stops rather than running late, and tell me which
ones you dropped and why.
What the assistant sets:
| In the prompt | In the plan |
|---|---|
| "two vans from the Mons depot" | Two vehicles on one depot. See Add vehicles and depots |
| "start at 7:00, finish by 16:30" | The vehicle shift window. See Shifts, working hours, and route limits |
| "pharmacy orders before 11:00" | A time window on those four orders. See Time windows, service time, priority, and load |
| "chilled only on the fridge van" | A required tag on the orders and the matching tag on the vehicle. See Tags: vehicle-order compatibility |
| "drop the lowest-value stops" | Higher priority on everything else. See Why an order went unassigned |
| "tell me which ones you dropped and why" | The Unassigned panel with its per-order explanation |
Prompts that state the outcome
State the outcome and let the assistant choose the fields that produce it.
Cost, not distance
I pay drivers 28 per hour and the vans cost 0.32 per km, plus 140 a day
each if I use them at all. Optimize for what this actually costs me, and
tell me whether the third van earns its keep.
Vehicle costs are optimizer inputs. See Vehicle costs and the COST metric. With them set, the answer to "is the third van worth it" is the COST difference between the runs.
Legal driving limits
These are long-haul runs under EU rules: 45 minutes of break before
4.5 hours of driving, and it can be split 15 plus 30. Apply that to
both trucks and show me where the breaks land.
See Driver breaks and driving-time limits.
Capacity and reloads
The van holds 18 roll cages. Let it come back to the depot to reload
mid-day if that serves more stops than a second van would.
See Multiple depots, open routes, and reloads.
Jobs that must stay together
The scaffolding drop and the pickup an hour later are one job, same
crew, drop first. Same for the three site visits at Rue Verte, they
run in that order.
See Pickup & delivery transfers and Order sequences.
Comparison runs
The assistant can run the optimizer more than once and compare the results:
Run this three ways and compare cost, distance, and unassigned orders:
(a) as it stands, (b) with a third van, (c) with the finish time
relaxed to 18:00. Give me a short table and a recommendation.
Each run is a full optimization on your data. The comparison answers questions like "do I need another driver", "what does the 16:30 cutoff cost me", or "how much does the new customer's 2-hour window add".
When orders go unassigned, ask "why was 88431 not served, and what is the cheapest change that would serve it". Routing24 produces a per-order explanation with blockers and levers. The assistant relays it in plain words. See Why an order went unassigned for the same material.
Constraints and plans
The plans differ in which planning rules they include. See Plans and billing.
The optimizer respects the constraints set on the plan. Later manual edits, yours or the assistant's, can break them: Routing24 reports the problem instead of refusing the edit. See Query, edit, and export a plan with AI.
Next step
Continue with Query, edit, and export a plan with AI. The full constraint reference is in Vehicles & Constraints.
FAQ
Do I have to know the optimizer settings to use the assistant?
No. State the outcome in your own words and the assistant chooses the fields that produce it. The reefer van that cannot run before 6am becomes a shift window, chilled only on the fridge van becomes matching tags, and drop the lowest-value stops becomes higher priority on everything else.
Which constraints can I state in plain language?
The assistant sets everything the optimizer reads: time windows, capacities and reloads, shifts and working hours, driver breaks and driving-time limits, tags for vehicle-order compatibility, pickup and delivery pairs, order sequences, priorities, and vehicle costs. The prompts work the same in the assistant in the app and in a connected assistant.
Can the assistant compare different optimization scenarios?
Yes. Ask for the plan run several ways, for example as it stands, with a third van, and with a later finish time. Each run is a full optimization on your data, and the comparison answers questions like whether another driver is needed or what a cutoff costs in distance and money.
What happens to the constraints when the plan is edited afterwards?
The optimizer respects the constraints on the plan. Later manual edits can break them: dragging a stop past its time window, or onto a vehicle whose tags do not match. Routing24 reports the problem on the route instead of refusing the edit, so you decide whether to keep it. The full constraint reference is in the Vehicles & Constraints category.