← All agents

Scheduling

Ridgeline

Capacity you already own, sitting in a truck

Ridgeline plans both boards as one problem, respects the constraints that never made it into any system, and proposes — never force-publishes — a day the branch manager can accept in one click.

+1.4
Inspections per inspector-day
-27%
Non-billable drive time
8 min
To re-plan a weather cascade
100%
Plans proposed, never auto-published

Interactive demo

Watch Ridgeline work a real case.

Step through it one action at a time. Nothing here is a mock-up of a chat window — these are the actual stages of a run, including the checks that happen before anything visible occurs.

Dispatch board + branch manager review0/8 steps

Rain cancels an exterior excavation at 6:10am

Tuesday, six crews, eleven inspections booked. Overnight rain makes an exterior waterproofing excavation unworkable, stranding a four-person crew and a material delivery scheduled for 10am.

Full transcript & decision trace

The part most vendors don't show you.

The verbatim conversation plus the reasoning trace behind it: rules fired, thresholds crossed, costs incurred, and every decision the agent deliberately refused to make.

Unlock the trace

Enter your details and it opens on this page. No spam — we only write when we have something worth saying.

What it's for

The problems Ridgeline exists to solve.

01

Two boards, two owners, one geography

Inspections are booked for homeowner convenience and production for crew utilization. Neither is planned against drive time, which consumes the day.

02

The reschedule cascade is manual triage

Rain moves one crew and six homeowners are affected. A coordinator solves it by phone, from memory, while new inquiries ring.

03

Optimizers get rejected in the first line

A plan that ignores certification, equipment, permits, or a promised return inspector is obviously wrong to a branch manager — and gets worked around permanently.

Capabilities

What it actually does.

Joint board planning

Inspection and production schedules solved together against territory, so slot offers and crew routing stop competing.

Hard-constraint modeling

Crew certification, equipment on the truck, permit status, weather sensitivity, homeowner windows, and warranty callbacks encoded before any optimization runs.

Cascade re-planning

When weather or a no-show breaks the day, produces a ranked set of recovery plans with the homeowner impact of each stated in plain terms.

Drafted customer comms

Writes every affected homeowner notification for a coordinator to review and send in one action.

Capacity forecasting

Projects bookable inspection capacity and crew-week throughput by territory so hiring is decided on evidence, not on the busiest week.

Integrations
  • ServiceTitan / JobNexus / branch CRMs
  • Dispatch and crew boards
  • Mapping & traffic services
  • Weather data
  • Permit portals
  • Payroll & timekeeping
Guardrails
  • Ridgeline proposes plans; a human accepts, edits, or rejects. It never overwrites a published board.
  • Warranty callbacks and promised return inspectors are hard constraints, never traded for route efficiency.
  • No homeowner is notified of a change until a coordinator sends the message.
  • Crew certification and equipment requirements cannot be relaxed by the optimizer under any objective.

Human handoff: The branch manager or dispatcher receives ranked plans with the trade-off of each stated, accepts one, and the drafted homeowner messages queue for a coordinator to release.

Questions

Straight answers.

Does it take over the schedule?

No. Ridgeline proposes plans with the trade-offs stated and a human accepts, edits, or rejects. A board that gets overwritten gets worked around.

What about the constraints nobody wrote down?

They surface as overrides, and every override is captured as a constraint on the record so the same wrong plan is never proposed twice.

What is the honest metric?

Completed jobs per crew-week and inspections per inspector-day, held against callback rate so throughput is never bought with quality.

Run Ridgeline against your own workflow.

Bring us one process and a number attached to it. We'll tell you whether an agent moves it.