Yearly running cost Assuming 2,400 schedules a year
By hand $72K / year 1,800 hours of work
Subscription n.a.
This workflow $164 / year Machine usage only; setup, hosting and review are extra. How should schedules be prepared? Assign jobs to available, qualified technicians and prepare a revised schedule when plans change.
One schedule includes up to 30 service jobs.
Review from exports Proposed dispatch schedule $1,512 – 4,560 setup Update the dispatch board Add an authorized system connection $1,872 – 5,760 setup
Which system should it connect to?Authorized field-service API Internal dispatch board A dispatcher approves schedule changes. Do not promise arrival times or reassign jobs automatically. Infeasible jobs must remain visible.
What is included Use a constraint solver for assignments and an AI explanation for the proposed changes. The base scope uses buyer-provided travel-time estimates; live routing and traffic subscriptions are separate.
Use a constraint solver for assignments and an AI explanation for the proposed changes. The base scope uses buyer-provided travel-time estimates; live routing and traffic subscriptions are separate.
Team size: up to 10 technicians.
Planning window: up to 1 working day.
Model input budget: up to 10,000 tokens across the reference run.
Model output budget: up to 1,800 tokens across the reference run.
Standard independent test set: at least 100 schedules.
Strict independent test set: at least 200 schedules.
Reference application CPU: 2 cores.
Reference application memory: 4 GB.
What standard do you need? Choose the acceptance targets your provider must demonstrate on your own test material.
Standard Test the defined workload and controls. Assignments meeting hard constraints: ≥100% Feasible jobs assigned: ≥90% Included Strict Tighter targets and a larger independent test set. Assignments meeting hard constraints: ≥100% Feasible jobs assigned: ≥95% Setup +$360 – 1,200 My own requirements Agree different targets and scope with your provider. Quote separately
How these standards are measured Hold out operating days with emergency additions, missing skills, impossible travel windows and mid-approval board edits. Compare with a feasible plan, not an unconstrained assignment count. Agree the holdout set before tuning. Report each metric with its numerator, denominator and exclusions; abstentions count against coverage. Test all inputs, including failures, rather than only accepted results.
Targets for your selected standard What is checked Target Assignments meeting hard constraintsAssignments satisfying skills, shifts and non-overlap rules divided by all proposed assignments. ≥100% Feasible jobs assignedJobs scheduled divided by jobs scheduled in an independently verified feasible reference plan, under identical constraints. ≥90% Unassigned jobs explainedUnassigned jobs with a correct actionable constraint explanation divided by all unassigned jobs. ≥98% Approval and data controlsPassed control cases divided by all independently tested unauthorized-action, stale-input and sensitive-data cases; any critical failure rejects delivery. ≥100%
Targets apply to the agreed independent test set, not every possible future input. During the pilot, a person reviews every result. Any unauthorized action or sensitive-data exposure fails acceptance.
How quickly do you need each schedule? Choose the time from accepted input to a reviewable schedule. Human review and waiting for source access are separate.
Within 2 minutes Included Within 60 seconds Setup +$144 – 480 Within 30 seconds Setup +$288 – 840
Timing details Measure wall-clock time including queueing, model calls, validation and permitted retries. Report failures and deadline misses. Faster targets need pilot testing; they are not vendor benchmarks.
The target applies to at least 95% of agreed test runs, with 1 in progress at a time.
How much should each schedule cost? Choose a machine-cost target per schedule. A lower cap may limit model calls and iterations.
Up to $0.50 Included Up to $0.40 Setup +$144 – 480 Up to $0.30 Setup +$288 – 840
Cost details Includes reference model usage, a retry allowance and allocated hosting at the stated volume. Human review, source-system subscriptions and paid connector access are separate. A tighter target must preserve the selected standards in the pilot.
Reference machine cost: $0.22 – 0.37 per schedule at 200 schedules a month. The selected cap is a target to test, not a replacement for this estimate.
Where do you want it to run? Run the workflow in your cloud or on your own machine. Choose separately whether it may use an external AI model.
Run it onYour cloud Local environment AI model accessApproved model API No external model calls
Data and access details Run in your controlled cloud environment with scoped access and retained review records.
Use an approved external model with the agreed data-processing terms and minimum necessary input.
Local hosting does not itself keep data offline. Connected business systems may still use the network. Private inference needs suitable hardware and a separate measured running cost; access and retention rules must be agreed before real data is used.
How do you want to use it? Choose a browser interface, an MCP tool for your current agent, or a standalone agent.
Web page Review each schedule in a private browser interface. Included Your AI agent Call the workflow through MCP; the same access and approval rules apply. Setup +$72 – 360 Standalone agent Use a dedicated agent with the agreed triggers and controls. Setup +$144 – 480