Built for Claude Desktop & Claude Code

Your Performance‑Pay EngineInside Claude

Connect your ServiceTitan or Housecall Pro once. Then just ask: find the profit leaks, design the incentive plan, run the pool, pay the techs. Every answer is benchmarked against hundreds of trades companies.

Claude · ShareWillow Engine
Message Claude…
Works in Claude Desktop & Claude Code · Free skills: npx skills add sharewillow/engine · Simple credits, cancel anytime
$15.5M
in performance bonuses paid through ShareWillow
+769%
top lift in repair sales per tech on a single plan
14,847
individual payouts, each one a labeled outcome
+$1,334
average extra earnings per tech, per month
Under the hood

Your field-service data, finally speaking one language

ServiceTitan and Housecall Pro don't agree on what a job, an invoice, or a callback even is. We've spent years normalizing every record and encoding the rules, so when Claude answers, the number is right.

ServiceTitan
Housecall Pro
Jobbersoon
QuickBookssoon
The ShareWillow layer
  • Jobs, invoices, estimates & techs mapped to one schema
  • Callback detection: recall links + tag keywords + a 5–30 day repeat-visit heuristic
  • Callback blame split fairly across the original crew
  • Revenue from what was actually invoiced, upsells included
  • Memberships credited to whoever really sold them
  • Close rates from estimates that became invoices
Answers you can pay onClean enough to calculate a bonus pool from, because that's exactly what we do with it, 14,847 payouts and counting.

Same question. Two answers. Only one you can pay on.

Ask a generic AI on raw APIs and it will confidently get it wrong. Watch both answers come back. Same shop, same data.

Without ShareWillow: raw APIs
Claude · raw ServiceTitan API
With the ShareWillow MCP
Claude · ShareWillow Engine

Hundreds of edge cases like these, already handled: encoded rules, normalized data, cross-company benchmarks. Without the ShareWillow MCP, the answers aren't just incomplete. They're confidently wrong.

What you get

One connection. Four things nobody else can bundle.

Plenty of tools have one of these. The Engine is the only place all four live behind a single connection in Claude.

1

Your data, made trustworthy

Clean, normalized reads of ServiceTitan and Housecall Pro (jobs, revenue, callbacks, memberships, close rates) with years of edge cases already handled. Clean enough to calculate a bonus from, because that's exactly what we do with it.

2

Playbooks as skills

Every comp design pattern we've proven across hundreds of shops (SPIFFs, tech scorecards, callback pools, membership incentives) installed into Claude with one command, free and open source.

3

Benchmarks nobody has

How your shop compares to hundreds of trades companies and, uniquely, which plan designs actually moved each metric. Not survey data. Real plans, real payouts, real outcomes.

4

Rails that pay

Design is a conversation. Execution is ShareWillow: pools calculated every period, distributions prepped for your one-click approval, techs paid on time. The plan doesn't live in a PDF. It runs.

The skills library

Skills we've already built, so you don't have to.

These aren't prompt templates. Each master skill is years of performance-pay operations encoded on the ShareWillow MCP: normalized field-service data, cross-company benchmarks, payout rails. You could spend months rebuilding the logic from scratch. You still couldn't rebuild the data.

5 master skills 27 sub-skills 40+ MCP tools 100s of companies' outcome data

All skills are free and open source, and every one can be scheduled to run on its own: weekly anomaly watches, month-end pool runs, quarterly benchmark refreshes. They come alive connected to the ShareWillow MCP.

Use cases

One engine. A whole back office of prompts.

Everything below is a real workflow the Engine runs today, in Claude Desktop or Claude Code, no terminal required.

The owner · Monday morning
Claude
Which techs are leaving money on the table?
Scanned 1,204 estimates, last 90 days
Ranked techs by unsold-estimate value
$83,400 in open estimates
Marcus: $31k unsold (closes 24% vs team avg 41%). Two coaching moves + a close-rate SPIFF would pay for itself in 3 weeks. Draft the SPIFF?
The consultant · 6 clients
Claude
Benchmark all six of my client shops against their cohorts
Pulled 12 months across 6 companies
Matched each to its trade + size cohort
2 shops below median on 3+ metrics
Peak Plumbing: callbacks 2.3× cohort median. Summit Air: 0.4 memberships/tech vs 2.1 benchmark. Full report per shop?
The always-on agent · Scheduled
Claude · weekly watch
⏰ Weekly anomaly watch · Friday 7am
Checked callbacks, tickets & memberships vs trailing 8 weeks
1 flag this week
Jake's callback rate jumped 3× (4 callbacks, all one install type). Suggest a ride-along before it hits the pool. Everything else on track.
✓ ServiceTitan ✓ Housecall Pro ✓ Claude Desktop ✓ Claude Code Jobber · coming soon QuickBooks · coming soon
The data nobody else has

The only dataset that knows what happened next

Anyone can pull your numbers. Only ShareWillow knows what hundreds of trades companies did about theirs: which plan designs they ran, what they paid, and what happened to callbacks, tickets, and memberships afterward. Every payout we've processed is a labeled outcome in the corpus your answers draw from.

Apollo Air · HVAC · 9 techs

+769%

repair sales per tech after launching their plan, with $156.8K paid to techs.

Lee's Air

+1,548%

memberships sold per tech (0.2 → 3.8 per month).

Trusted Heating & Cooling

+254%

average ticket ($80 → $284) after tying performance pay to it.

Bears Home Solutions

+564%

revenue per tech; company revenue up 91% on 10 techs.

Sapphire Coast · 12 techs

+336%

tech-generated leads, with $146.2K paid out on the plan.

NH Ross · 34 employees

35×

payout growth in 5 months ($2,890 → $100,329/mo) across 7 plans.

When the Engine says "shops like yours pay $25 per membership and it moves the number 2–4×," that's not a model's opinion. It's the median of shops that actually did it. Always anonymized: no shop, tech, or customer is ever identifiable.

"I would 100% encourage people to do performance pay, and definitely partner with ShareWillow."

Chris McDowell · Business Operations Manager, Clog Busters (31 techs · $1.01M in bonuses paid)

The math

One prompt replaces a comp consultant.

And unlike a consultant, it doesn't leave after the invoice. It runs the plan every payroll period.

The old way

A comp consultant

  • $10–25k engagement, paid up front
  • Six weeks to a recommendation
  • Based on experience with a handful of shops
  • Delivers a PDF you still have to run yourself
  • Gone after the invoice; nobody watches the plan
The Engine

ShareWillow Engine

  • Audits your real data in minutes, not weeks
  • Benchmarked against hundreds of companies and 14,847 payouts
  • Simulates the plan on your own jobs before you commit a dollar
  • Runs it every payroll period, forever: pools, approvals, payouts
  • Watches for anomalies weekly, from $199/mo

And you stay in control the whole way: the Engine drafts, you publish, and every dollar requires your sign-off.

Pricing

Simple credits. Start free. Pay when it pays.

The skills are free and open source. Credits meter what's valuable: your live data and our benchmarks. Unused credits roll over; they never expire.

Skills
100
credits included
Freeno card required
  • All open-source skills
  • Unlimited demo-data mode: a full audit on a sample shop in 5 minutes
  • Enough credits to taste your real data
Install the skills
Engine Multi
8,000
credits / month
$499/month$0.06 / credit
  • Everything in Engine
  • Up to 10 companies
  • Portfolio-wide benchmarks
  • For consultants, coaches & roll-ups
Get on waitlist
1 credit · data query (jobs, revenue, callbacks…) 5 credits · benchmark query 25 credits · plan simulation ~150 credits · full audit

Already a ShareWillow customer? Unlimited credits are included in your subscription, plus the one thing no prompt can do without us: actually paying your techs.

Questions

Fair questions, straight answers

Do I need to know how to code?

No. The Engine works in Claude Desktop, the same app you'd use to chat. Connect your field-service software once, then talk to it like you'd talk to your best ops manager. Claude Code works too if that's your thing.

Is my shop's data used in the benchmarks?

Benchmarks are always anonymized and aggregated: no shop, tech, or customer is ever identifiable, and small groups are never reported. Your raw data is yours; it's never shared or sold.

Can the Engine spend money or change my plans without me?

No. The Engine drafts; you publish. Every plan goes live only when you approve it in ShareWillow, and every distribution requires your explicit sign-off before a dollar moves.

How far do 2,500 credits go?

A long way. A full audit is ~150 credits, a plan design with simulation ~50, and day-to-day questions cost 1–5 each. Most single shops use 800–1,500 credits a month, and unused credits roll over, so heavy months are covered.

What if I don't use ServiceTitan or Housecall Pro?

Jobber and QuickBooks are next, with more platforms to follow. You can also start in demo-data mode or with CSV exports to see what the Engine finds.

How is this different from hiring a comp consultant?

A consultant gives you a plan in six weeks for $10–25k, based on experience with a handful of shops. The Engine audits your real data in minutes, benchmarks against hundreds of companies and 14,847 payouts, then runs the plan every payroll period, forever.

The waitlist

Your techs are one prompt away from acting like owners.

We're onboarding a small group of shops, consultants, and roll-up operators this quarter. Grab a spot.

Get on waitlist

or install the free skills: npx skills add sharewillow/engine