Wave
Docs menutap to expand

Concepts

Wave Intelligence

Wave reasons about the job — residential vs. commercial, water category, scope. The estimate reflects what an experienced estimator would build.

Last updated

Anyone can build a chat front-end that adds a drywall line item when you type "I tore out drywall." That's a string match. It's not what Wave is doing.

Wave reasons about the job.

When you describe a loss, Wave infers context — residential vs. commercial, water category, what kind of property this is, how the structure is built, what an experienced estimator would put on a defensible bid — and shapes the line items to match. The estimate that comes out the other end isn't a transcription of what you said. It's what someone who's run a thousand jobs would write down for this job.

That's Wave Intelligence. The rest of this page is what it looks like in practice.

Residential water loss

Jordan Park at 482 Sycamore Lane has a Cat 2 toilet supply line failure affecting the hall bathroom and hallway. You tell Wave that in one sentence.

Wave knows this is a single-family residential property. Residential structures have a specific anatomy — sill plates, insulation in the wall cavities, drywall on standard 16" centers, baseboards, often carpet pad over hardwood. Residential contents are personal: a vanity, a toilet, baseboards, trim.

So the estimate Wave generates includes:

  • Insulation removal in the affected wall cavities — water tracks into residential insulation and it has to come out
  • HEPA vacuuming of the affected surfaces — residential cleanup standards demand it
  • Antimicrobial application at the right Cat-2 dosage
  • PPE quantities scaled for two technicians working two days in a contaminated environment
  • Containment between the bathroom and the hallway because the loss crossed a doorway

You didn't say "I'll need insulation removal." Wave knew.

Commercial water loss

Now the same Cat 2 toilet supply line, but in a 30,000 sq ft office building. The affected rooms are a small break room and the adjacent open-plan workspace.

The structure is different. Commercial construction often skips insulation in interior walls. The flooring is commercial carpet tile or polished concrete, not pad-over-hardwood. The contents aren't personal — they're systems furniture and equipment.

Wave shapes the estimate accordingly:

  • No insulation removal when the building type wouldn't have insulation in those walls
  • Equipment-monitoring hours scaled for a larger building (commercial drying takes longer and needs more documentation)
  • Containment posture weighted toward keeping the rest of the floor operational during work hours
  • Different antimicrobial profile based on commercial cleaning standards

Same chat input, same loss category, materially different line items — because the building type changes what an experienced estimator would bid.

Category-aware adjustments

Cat 1, Cat 2, and Cat 3 are not labels Wave attaches and forgets. They reshape the estimate:

  • Cat 1 (clean water) — minimal PPE, no antimicrobial, no containment required by the standard
  • Cat 2 (gray water) — Tyvek + N95 PPE, antimicrobial application, basic containment, careful documentation
  • Cat 3 (black water) — full PPE, higher-class antimicrobial dosing, hard containment with negative air, expanded demo scope, IICRC-required documentation that wouldn't apply at Cat 1 or 2

Flipping a Cat 2 estimate to Cat 3 doesn't just change the category dropdown. Wave reproposes the line items that depend on category — and you'll see PPE quantities go up, antimicrobial change, containment add, demo expand. That's the reasoning system updating its view of the job, not a UI re-render.

Scope-aware repricing

When you add a room mid-estimate, the per-room totals on existing rooms can shift slightly — usually downward. People sometimes ask whether this is a bug. It isn't.

Some line items are sized against the whole project, not against any single room. Equipment is the obvious one: an air mover serving three rooms isn't three separate line items, it's one piece of equipment whose per-room cost allocation changes as the room count changes. Containment scales similarly. So does the documentation footprint.

When Wave re-evaluates the project as a whole — which is what happens on every meaningful change — the per-room math redistributes. The Grand Total moves up (you added scope), and the existing-room subtotals tick down (their share of the project-wide line items got smaller). An experienced estimator would do the exact same math in their head. Wave does it automatically.

Defensive bidding

One observable consequence of Wave Intelligence is that estimates are defensively bid — Wave errs in the direction of including more line items, not fewer.

This is by design. The asymmetry is brutal: forgetting one line item can wipe out the margin on the whole job (the carrier won't approve a supplement, ops gets billed for materials that weren't bid, you eat the cost). Including one line item you didn't need costs nothing — the estimator at the desk deletes it. So Wave reasons in the direction that protects you: it's better for a line to be present and trimmed than missing and left on the table.

The fuller explanation, including the worked examples, lives at How Wave thinks about scope.

What this is hard to replicate

A chat-to-form-filler is a string-matching exercise. You can build one in a weekend with any LLM.

Wave isn't that. The reasoning that decides insulation comes out in residential, not commercial is grounded in restoration knowledge — IICRC drying science, structural anatomy, regional pricing reality, the specific way carriers actually approve estimates. It's the difference between a chatbot that types "drywall repair" into a form and a system that knows what comes with drywall repair in this category at this building type at this scale.

That's the moat. It's why Wave produces estimates an experienced estimator would have produced — not estimates a model trained on internet text would have produced.

Related