Skip to content
Cranley

Takeoff bid

Quantities for a trade from the scan (floor by finish, paintable wall, glass, doors, fixtures), priced with your own rates: a cleaning bid, an apartment unit turn, or a fit-out estimate.

What it answers

Section titled “What it answers”
  • What would it cost to clean this office three nights a week?
  • Scope the turn for this unit
  • Rough fit-out price for this suite

For the agent, the tool is described as: Measure trade quantities in one scan with geometry.takeoff plus floor finishes and restroom fixtures seen in the panoramas, then price them with editable rates. trade = cleaning (hours per visit and a monthly price), unit_turn (paint gallons, flooring, doors, blinds, fixtures) or fit_out (flooring, ceiling, paint, optional new offices). Quantities are measurements with sources; every price is an assumption.

Who it is for

Section titled “Who it is for”

Apartment manager, Commercial cleaning bidder, Facility manager, Office tenant.

Inputs

Section titled “Inputs”
Input Type Required Default Notes
scan string yes Scan id. Filled from the selected building.
trade string yes Asked as: “Which bid: a cleaning bid, an apartment unit turn, or a fit-out estimate?” Saved preference bid.trade. One of: cleaning, unit_turn, fit_out.
carpet_ft2_per_hour number (ft²/h) 3500 Carpet vacuuming rate. Saved preference bid.clean.carpet_rate. Range: more than 0.
hard_ft2_per_hour number (ft²/h) 2500 Hard floor mopping rate. Saved preference bid.clean.hard_rate. Range: more than 0.
fixture_minutes number (min) 4 Minutes per restroom fixture. Saved preference bid.clean.fixture_min. Range: at least 0.
glass_ft2_per_hour number (ft²/h) 600 Glass cleaning rate. Saved preference bid.clean.glass_rate. Range: more than 0.
glass_visits_per_month number 1 Window cleaning visits per month. Saved preference bid.clean.glass_visits. Range: at least 0.
visits_per_week number 3 Cleaning visits per week. Saved preference bid.clean.visits. Range: at least 0, at most 7.
wage number ($/h) 22 Loaded labour cost per hour. Saved preference bid.wage. Range: at least 0.
markup number 0.35 Overhead and margin on labour. Saved preference bid.markup. Range: at least 0, at most 3.
paint_per_ft2 number ($/ft²) 0.95 Paint, two coats, labour and material, per wall ft². Saved preference bid.turn.paint. Range: at least 0.
paint_ft2_per_gallon number (ft²/gal) 350 Coverage per gallon per coat. Saved preference bid.turn.coverage. Range: more than 0.
carpet_per_yd2 number ($/yd²) 32 Carpet replaced, installed. Saved preference bid.turn.carpet. Range: at least 0.
replace_carpet boolean false Replace carpet (heavy turn) instead of cleaning it. Saved preference bid.turn.replace_carpet.
carpet_clean_per_ft2 number ($/ft²) 0.3 Carpet cleaning. Saved preference bid.turn.carpet_clean. Range: at least 0.
hard_floor_per_ft2 number ($/ft²) 0.6 Hard floor clean and touch-up. Saved preference bid.turn.hard. Range: at least 0.
per_door number ($) 30 Door and hardware touch-up, each. Saved preference bid.turn.door. Range: at least 0.
per_window number ($) 35 Blind replaced, each window. Saved preference bid.turn.blind. Range: at least 0.
per_fixture number ($) 25 Fixture service, each. Saved preference bid.turn.fixture. Range: at least 0.
flooring_per_ft2 number ($/ft²) 4.5 New carpet tile or LVT, installed. Saved preference bid.fit.floor. Range: at least 0.
ceiling_per_ft2 number ($/ft²) 3.0 Ceiling tile replaced. Saved preference bid.fit.ceiling. Range: at least 0.
partition_per_lf number ($/lf) 95 New partition, framed and finished. Saved preference bid.fit.partition. Range: at least 0.
new_door number ($) 1400 New door, frame and hardware. Saved preference bid.fit.door. Range: at least 0.
add_offices integer 0 Private offices to build in the open area. Saved preference bid.fit.add_offices. Range: at least 0, at most 50.
contingency number 0.15 Contingency on the fit-out. Saved preference bid.fit.contingency. Range: at least 0, at most 1.
label_with_vision boolean true Label rooms and read floor finishes from the panoramas first.

An input that nothing fills (the selected building, a saved preference, a persona’s preset) becomes a question to the person. The agent asks only for those.

Data used

Section titled “Data used”
Layer Id Needed If it is missing
Wall outline matterport.walls optional floor area only
360° photos matterport.panos required The verdict is unknown, with the reason.

What it returns

Section titled “What it returns”

A tool result: a verdict (pass, warn, fail or unknown), metrics, checks and findings, each with its source.

  • Draws on the building: a colour per room; pins on what it found.
  • Panel blocks: VerdictHeader, MetricRow, MiniChart, FloorPlanMini, AssumptionChips, Controls, EvidenceStrip, StepLog.
  • Speed: slow. Read-only.

How it works

Section titled “How it works”

Takeoff bid: trade quantities from one engine (geometry.takeoff, plus floor finishes and fixtures seen in the panoramas), priced with rates that are the bidder’s own editable assumptions. Three price books: a cleaning bid, an apartment unit turn, and a fit-out refresh.

Reliability

Section titled “Reliability”

Sources this tool gave on the test cafe:

Where it came from Layer Method Reliability Note
Measured from the scan matterport geometry high geometry.takeoff on the wall graph
Simulated model simulation low Your rates times measured quantities; rates are assumptions
Seen in a model model vision medium Fixtures counted in the room’s central panorama

The tool sets the label for each value. A model never does. The tools give a scan’s wall graph the layer matterport whichever device made the scan, so a phone scan’s geometry carries that label too.

Limits

Section titled “Limits”
  • Needs: 360° photos. On a scan without it, the verdict is unknown and says why.
  • It is slow: progress steps reach the workspace while it runs.
  • A result is a planning aid, not an inspection.

On the made-up test cafe

Section titled “On the made-up test cafe”

This section was written by running the tool when the docs were built, on a hand-made RoomPlan export (no real place was scanned), with no sponsor keys and the network switched off.

Inputs used: trade = "cleaning" (preset of the persona “Commercial cleaning bidder”); visits_per_week = 3 (preset of the persona “Commercial cleaning bidder”).

Pass About 0.4 labour hours per visit and $144 a month at 3 visits a week, for 905 ft² (0 carpet, 0 hard floor, 905 finish not read) and 0 restroom fixtures. Quantities are measured; every price is your assumption. Not measured: interior glass and partitions.

Value Result Where it came from Reliability
Cleanable floor 905 ft² Measured from the scan high
Labour hours per visit 0.36 h Simulated low
Monthly price 144 $ Simulated low
Restroom fixtures 0 Seen in a model medium
Exterior glass (one side) 87 ft² Measured from the scan high
Floor: not read 905 ft² Measured from the scan high

What it reported while it ran:

  1. Measured 4 rooms: 905 ft² of floor
  2. Read floor finishes for 0 rooms
  3. Counted fixtures in 0 of 1 restrooms or bathrooms

Run it

Section titled “Run it”
threshold run takeoff_bid --scan <scan-id>
curl -X POST http://127.0.0.1:8787/api/tools/takeoff_bid/run -H 'content-type: application/json' -d '{...inputs}'

Over MCP the tool is named takeoff_bid. See MCP server and CLI.