How should draft layouts be prepared? Prepare detector layout and schedule drafts from checked room data for your fire-alarm engineer to review.
One floor draft includes up to 20 validated rooms.
Review from exports Layout and device schedule draft $2,160 – 6,240 setup Connect a design review folder Add an authorized system connection $2,448 – 7,200 setup
Which system should it connect to?Approved engineering document API Internal design review folder Drafts only. A qualified fire-alarm engineer checks every output. No construction release, code certification, safety-system control or design from unverified geometry.
What is included The base input is checked room polygons and approved device rules, not arbitrary PDFs or building-model interpretation. Export a preliminary DXF and device schedule. Riser design, voltage-drop calculations and complex spaces are separately scoped.
The base input is checked room polygons and approved device rules, not arbitrary PDFs or building-model interpretation. Export a preliminary DXF and device schedule. Riser design, voltage-drop calculations and complex spaces are separately scoped.
Floor area: up to 2,000 square metres.
Design basis: up to 1 engineer-approved rule set.
Model input budget: up to 12,000 tokens across the reference run.
Model output budget: up to 2,500 tokens across the reference run.
Standard independent test set: at least 100 floor drafts.
Strict independent test set: at least 200 floor drafts.
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. Correct room and unit mapping: ≥100% Draft placements meeting supplied rules: ≥98% Included Strict Tighter targets and a larger independent test set. Correct room and unit mapping: ≥100% Draft placements meeting supplied rules: ≥99% Setup +$360 – 1,200 My own requirements Agree different targets and scope with your provider. Quote separately
How these standards are measured Hold out complete floors reviewed independently by a qualified engineer. Include malformed polygons, unit mismatches, missing ceiling details, obstacles and unsupported rooms. Unsafe or incomplete inputs must be rejected, not guessed. 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 Correct room and unit mappingCorrectly mapped room identifiers and dimensions divided by all required geometry fields; unit mistakes fail the pilot. ≥100% Draft placements meeting supplied rulesPlacements satisfying the supplied deterministic checks divided by all proposed placements; this does not certify code compliance. ≥98% Drawing and schedule agreementMatching device identifiers and counts divided by all devices in the drawing and schedule. ≥100% 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 floor draft? Choose the time from accepted input to a reviewable floor draft. Human review and waiting for source access are separate.
Within 3 minutes Included Within 2 minutes Setup +$144 – 480 Within 60 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 floor draft cost? Choose a machine-cost target per floor draft. A lower cap may limit model calls and iterations.
Up to $1.00 Included Up to $0.80 Setup +$144 – 480 Up to $0.70 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: $0.39 – 0.69 per floor draft at 100 floor drafts 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.