Can AI forecast my shop's cash flow?
Auto Advisor's Strategy agent builds a 13-week cash outlook from your trailing repair-order revenue with a documented deterministic method, scores your net margin against the healthy 15 to 20% band, and computes a hire signal from real technician load. Every figure comes from tested pure functions; no AI model is in the loop at all.
What does the Strategy agent actually do?
One plain-numbers owner briefing: where cash bottoms out over the next 13 weeks, whether it is time to hire, and how margin and rates hold against benchmarks.
- 01
Builds a 13-week cash forecast from trailing closed-RO revenue with a documented deterministic method, reporting the lowest-cash week and amount.
- 02
Scores net margin against the 15 to 20% healthy band, with the gap in dollars.
- 03
Computes weighted technician efficiency and a hire / healthy / soft capacity signal.
- 04
Compares your effective labor rate and ARO to documented public benchmarks.
- 05
Produces a multi-location comparison when you run more than one site, degrading honestly to a single-site view.
What it reads to do the work
- Your service orders, technicians, locations, and labor-rate history
- An opening-cash figure and weekly-outflow override you can supply per run
- The autonomy mode you set for it (Off produces no briefing at all)
How do I stay in control of what it does?
Every agent runs in the mode you choose, Off, Approve, or Auto, and every agent starts in Approve so a human signs off before anything happens. Here is what Strategy can do, with the gate on each action, and the rails that hold in code, not in a policy document.
The actions, and their gates
- Compile the owner briefing (read-only, writes no shop data)Read-only
- Record one acknowledge-gated briefing row per day; acknowledging marks it read and can never cause a writeYou approve it
The guardrails, held in code
- No AI model in the loop: every figure comes from tested pure functions.
- One briefing per shop per day, idempotent.
- The briefing acknowledgment executes an explicit no-op, so approving it can never write anything.
What does Strategy not do yet?
Every claim on this page maps to shipped, tested code, and the same discipline applies to the limits. Here is where the edge of the product is today, stated plainly, so nothing on your shop rests on a promise.
- The forecast runs on documented assumptions (cost of goods at 55% of revenue, weekly outflow at 80% of trailing weekly revenue) plus an opening-cash figure you supply. It reads your repair orders, not your bank or your books, so treat it as a directional planning tool.
- Rate comparisons are against published industry benchmarks, not a live local-market feed.
- Forecast accuracy is not yet scored against actuals, so we do not claim an accuracy number.
- It runs when triggered, not yet on its own morning schedule.
Which numbers does Strategy actually move?
Only measured numbers are listed here; a metric the product does not compute does not get claimed.
- Net margin versus the 15 to 20% band
- Lowest-cash week and amount over the 13-week horizon
- The capacity (hire) signal
The rest of the crew
Strategy is one of fifteen agents. Each has its own charter page, its own autonomy dial, and the same honesty rule.
Put Strategy to work in your shop.
Request a Service-Drive Audit. We map exactly where the crew recovers time and revenue, on your numbers, in a live demo on sample data.
No obligation · no high-pressure pitch · plain, public pricing