Monday Customer Health Brief

You're the owner. When the shop was small you could feel who was happy. You remembered the house where the part was late, the patient who sat too long, the invoice that never got a second notice. Then you added a truck, or a hygienist, or a second location, and the feeling went. You still think you'd "know" if someone was about to leave a three-star or ghost a $4,000 invoice. You wouldn't. You'd find out on Google, or when they called the shop down the road.

This playbook is a Monday habit, not a customer-success department. You dump last week's jobs, reviews, and invoices into Claude or ChatGPT (Reactive). You get a one-pager of five accounts to touch (Proactive). You get drafted emails a human still sends (Active). That's the whole machine. Delivery is the truth serum. Not a sentiment dashboard, not a "health score" you can't explain to your spouse.

Map the idea into a shop: "did we ship" becomes jobs completed on time, callbacks, late parts, three-star reviews, unpaid invoices. If you didn't finish the work, didn't come back when you said you would, left them waiting on a part, collected a shrug on Google, or let the bill sit, they are not healthy. You don't need a model to invent a vibe on top of that.

Effectiveness. You keep the customers who already paid you, and you catch the unpaid invoices and the wobbling accounts before they become a lost replacement or a lost family of four. Efficiency. Monday is forty-five minutes, not a scavenger hunt through four logins. Quality. The person who had a late part gets a human note, not silence, and you never automate an apology you don't mean.

Who it's for

You run a service business — HVAC, dental, a shop with jobs and invoices — and you have enough customers that you can no longer keep the pulse in your head. You already have last week's jobs somewhere: Jobber, Housecall, ServiceTitan, a PMS, a spreadsheet the office manager hates.

You are not trying to "do customer success like a SaaS company." You are trying to start the week knowing which five humans deserve a call or a note, and having the note drafted so you actually send it.

What you get when done

A repeatable Sunday-night or Monday-morning dump. A one-page brief: five accounts, why they matter, what to do. Drafted emails or texts sitting in your drafts folder. A rule that nothing customer-facing sends itself. After two Mondays, you will know whether the signal is useful. If it isn't, you will change the prompt, not buy a platform.

Time and tools

First build: two hours to pick the source of truth, write the dump format, and run it once on last week. Then 45 minutes every Monday: 15 to dump, 15 to read the brief, 15 to edit and send.

Tools:

• Last week's jobs. Export CSV or copy a list from Jobber / Housecall / ServiceTitan / your PMS. Columns you actually have: customer, job type, completed or not, on-time or late, callback yes/no, notes.
• Reviews. Google Business Profile — last 7 days, including 3-stars you hoped nobody saw.
• Invoices. Unpaid and overdue from the same system. Aging, not a vibe.
• ChatGPT or Claude. I use Claude for long messy dumps; ChatGPT is fine. One chat per Monday, named with the date.
• Email or the shop SMS number. Drafts only.
• Optional, later: Zapier or Make to email you the dump reminder. Not in week one. Week one is you, a CSV, a prompt.

Prerequisites

You can export or copy last week's completed jobs. You can see unpaid invoices. You can see new Google reviews. You have a definition of "done work" that isn't "we feel busy." You will name one human who sends — you, the office manager, the coordinator — not "whoever has a minute."

If your jobs live only in techs' heads and a whiteboard, fix that enough to list last week's addresses and outcomes. The model cannot brief a week you refuse to write down.

Step 1 — Reactive: dump last week's jobs, reviews, and invoices

Why. Before you chase feelings, answer the question that cannot be sweet-talked: did we deliver what we promised? In a shop that means jobs completed, callbacks, late parts, reviews, and whether we got paid. One week's data, one model, no automation. If the dump is a lie, the brief will be a lie with nicer headings.

Exactly what to do.

1. Pick the source of truth for jobs. One system. If Jobber is the board, Jobber wins even if a tech also texts you.
2. Export last week, Sunday to Saturday, or copy these columns into a sheet: date, customer name, job/visit type, completed (yes/no), on time (yes/no), callback (yes/no), late part (yes/no), one-line note from the tech or front desk.
3. Add a tab or a second paste: Google reviews in the last 7 days (stars, text, which location if you have more than one).
4. Add unpaid invoices: customer, amount, days overdue, job the invoice belongs to if you know it.
5. Strip anything you wouldn't want in a random tool: full card numbers, SSNs, clinical notes, a patient's medical history. Names and addresses of HVAC customers are operational; you can initials them if you're jumpy. Dental: use initials and visit type, not chart notes.

Open Claude or ChatGPT. New chat. Title it Customer health — [date]. Paste the weekly prompt below, then paste the three dumps.

The weekly prompt (copy this every Monday):

You are briefing the owner of a local [HVAC shop / dental practice / service business] on LAST WEEK only.

I will paste three dumps:
1) Jobs/visits (date, customer, type, completed, on time, callback, late part, note)
2) Google reviews from the last 7 days
3) Unpaid invoices (customer, amount, days overdue, related job if known)

Rules:
- Use only what I pasted. If a field is missing, write "unknown." Do not invent a reason, a quote, a dollar figure, or a review that is not in the dump.
- Delivery is the truth: completed work, on-time, callbacks, late parts. Do not write a "sentiment score" that ignores a missed callback.
- This is a shop, not a software company. "Shipped" = the job or visit we said we'd finish.

Output:
A. One paragraph: did we deliver last week, in plain English.
B. A table of every job/visit that was late, incomplete, a callback, or had a late part. Include customer and the issue in one line.
C. Reviews: list each one. Flag 3-star and below, and any 5-star that mentions a specific person we should thank.
D. Invoices: list overdue, oldest first. Do not round the amounts.
E. "Accounts that deserve a human check-in" — max 8, ranked. For each: why (point at a row), and whether the risk is delivery, review, or money.
F. What you are unsure about. Questions only. No guesses.

Do not recommend firing anyone. Do not draft emails yet.

Read the output with the office manager or dispatcher. If it names a customer who isn't in the dump, the model is padding. Start a new chat and tighten. If it misses a callback you can see in the sheet, your columns are messy — fix the sheet, don't hunt for a smarter model.

Done looks like. One chat, one week, a list of accounts that came from rows you recognize. You could defend every name on the check-in list by pointing at a job, a review, or an invoice. That is Reactive. You are talking to your data. You have not automated anything.

Step 2 — Proactive: Monday one-pager of 5 accounts to touch

Why. A complete dump still loses if it takes forty minutes to read. You need the Presidential Daily Brief of a two-truck shop: five names, why, what you'd do before lunch. Once you trust the smoke signal from Step 1, you stop lighting the fire by scrolling Jobber on Sunday night and hoping you remember the late evaporator coil.

Exactly what to do.

Same chat, or a second prompt in that chat after you've corrected any hallucinations out loud ("drop the Smiths, that callback was a filter we already replaced"). Paste the one-pager prompt.

Turn the check-in list into a MONDAY ONE-PAGER the owner will read in five minutes.

Hard cap: FIVE accounts. If you have more, keep the five that mix (a) money at risk, (b) a customer who had a bad delivery last week, (c) a review that needs a human, (d) a good account we could wow this week — at most ONE wow. Do not fill the page with wow if delivery is on fire.

For each of the five:
- Account / household / patient initials
- Why this week (point at last week's fact)
- Risk type: delivery / review / unpaid / opportunity
- Suggested human action in one sentence (call, text, email, wait)
- Do NOT draft the message yet
- Do NOT score them 0–100. High / medium / low is enough, and only if you can say why from the dump

Then a 5-line Executive Summary at the top:
- 3 risks
- 1 opportunity (or "none this week")
- 1 pattern across accounts (late parts, no-shows, invoices over 30 days, etc.) or "no pattern"

If five accounts would require inventing problems, give fewer. Empty is allowed.

Put this one-pager where you will see it: printed on the desk, a note in the Monday huddle, an email you send yourself. The point is that Monday starts with names, not with inbox.

You do not need Zapier yet. If after four Mondays you still trust the prompt, you can have a tool remind you to dump the CSVs. I would not wire Jobber directly into a model until you have watched it lie at least once and caught it. Automation of a sloppy dump just mails you slop at 8 a.m.

Done looks like. A one-pager with five or fewer names, each tied to a fact from last week. You read it before you unlock the rest of Monday. Someone on the floor agrees the five are real.

Step 3 — Active: drafted emails, human sends

Why. Insight that doesn't become a call is a diary. The last move is hospitality prep: the messages are ready so you spend your judgment on tone, not on a blank page. The model does not get to hit send. That's Quality. An auto-sent "sorry we were late" to the wrong house is how you create a review.

Exactly what to do.

For each of the five, decide channel: phone call (no draft needed beyond a 3-line talk-off), SMS from the shop number, or email. Then paste the outreach prompt once with all five, or once per account if the context is long.

The outreach prompt (copy this):

Draft outreach for the five accounts on my Monday one-pager. I am the owner of [shop], [city]. Voice: first person, short, specific, no "just circling back," no "your business is important to us."

One-pager:
[paste the five]

Extra facts I know that were not in the dump (optional):
[paste — or "none"]

For each account write:
- Channel: call talk-off (5 bullets) OR SMS (under 50 words) OR email (subject + 80–120 words)
- The actual draft
- A note labeled HUMAN MUST CHECK: what fact in this draft could be wrong
- A line we will NOT say (don't blame the tech by name, don't promise a credit you didn't approve, don't diagnose, don't offer a discount I didn't list)

Rules:
- If last week was late or a callback, own it. Do not hide behind "unforeseen circumstances."
- If the invoice is overdue, be direct and kind. Name the amount I provided. Do not round. Do not threaten collections unless I wrote that policy.
- If the review was 3-star, draft a *private* reply asking to make it right, and a short public reply that does not argue. I will post the public one myself.
- If this is the "wow" account, do not sound like a coupon. Offer a real next step I listed (tune-up, recare, a thank-you).
- NEVER send. Label every draft DRAFT — HUMAN SENDS.
- Do not invent a job we completed, a part that arrived, or an apology for something that isn't in the facts.

Paste the drafts into Gmail drafts, your PMS message window, or the SMS tool — unsent. Walk them with the person who owns the relationship. Change the sentence you would never say. Then send, or pick up the phone and ignore the draft.

Examples of what this is for, in a shop:

• Late part: "The coil we ordered for [address] landed [day]. I can be there [window]. If that window is wrong, reply with two that work."
• Callback: "We came back because the first visit didn't finish it. I want to hear whether the house is doing what we said it would."
• 3-star: public = thank them and ask to continue offline. Private = make it right. Never argue the star count.
• Unpaid: the amount, the job, how to pay, a human name. Not a novel.
• Wow: the family that paid a replacement on time and left a specific 5-star — a thank-you from you, not a review-beg in disguise. If you want a review ask, that's a different playbook, and you still never fabricate one.

Done looks like. Five drafts. At least one you rewrote. All five either sent by a human or consciously skipped. Zero auto-sends.

Worked example (hypothetical dental practice)

Hypothetical: Oak Street Dental, one doctor, two hygienists, a coordinator named Mara. They don't think they have a "customer health" problem. They have three unpaid balances over 30 days, a 3-star from a new patient who waited 40 minutes, two failed recare confirms, and a crown seat that had to be remade. That's a week.

Sunday night, Reactive. Mara exports last week's visits from the PMS: date, initials, visit type, completed, on time, callback (the remake), note. She copies three new Google reviews (one 3-star, two 5-stars). She copies the aging: three names, amounts, 34 / 48 / 61 days. She strips chart notes. She pastes the weekly prompt.

The model flags the remake, the wait, the three balances, and a recare family that no-showed twice. It also tries to invent a "health score of 72." Mara deletes that instruction in her head and in the next run she already has "do not score 0–100" in the prompt. Good.

Monday 8:10 a.m., Proactive. Five accounts, not eight:

1. New patient with the 3-star — Quality, human call from Mara, not a template.
2. Crown remake — delivery, doctor calls, not the coordinator.
3. 61-day balance — money, Mara, the amount from the dump.
4. Recare no-show twice — Effectiveness (empty chair) and a human decide if this is a deposit rule they already have, not a fee the model invents.
5. Wow: the 5-star that named a hygienist — a thank-you, and only if the visit was actually smooth.

Active. Drafts: a public review reply that doesn't argue; a private "come in, we'll make this right" Mara edits because the model offered a free whitening the practice doesn't use as an apology; a doctor talk-off for the remake ("we remade it, here's when, no lecture"); an invoice SMS with the real number; a two-line thank-you to the 5-star family that does not include a review link because they already reviewed.

Mara sends four. The doctor makes the remake call. Nothing auto-fires. That's the install.

I am not claiming Oak Street is a client. I'm showing you the week so you can copy the shape.

How this maps if you don't "ship software"

If you are HVAC, late parts and same-week callbacks are the truth serum. If you are dental, wait time, remakes, recare holes, and balances are the truth serum. If you are an agency, stalled deliverables and unsigned change orders. Same three steps.

Failure modes / what NOT to automate

Do not auto-send. Not the apology, not the invoice nudge, not the review reply.

Do not let the model invent a health score you cannot point at a row for. High / medium / low with a fact is enough. "72" is costume jewelry.

Do not dump clinical notes, legal files, or card numbers into a chat. Initials and visit type. Job address if you need it for HVAC. When in doubt, cut the field.

Do not treat Jobber or the PMS as the whole relationship. A customer can have on-time jobs and still be done with you because your estimator was rude. The dump will miss that. That's why a human sends, and why empty "wow" slots are allowed.

Do not wire four tools in Zapier on Monday one. You will spend the month authenticating and skip the brief. Manual dump until the prompt is boring.

Do not "reach out" to everyone who paid you last week. That's how you become noise. Five accounts.

Do not have the model offer discounts, free visits, or refunds you didn't put in the facts. It will be generous with your margin.

Do not argue with a 3-star in public. Draft, human, short.

Do not skip a week because last week "felt fine." The weeks that feel fine are when the 61-day invoice quietly becomes 90.

FAQ

I don't have Jobber or a PMS export. Can I still do this? Yes. A sheet with last week's names, what you did, whether you had to go back, and whether they paid is enough. If you cannot list last week's jobs at all, the playbook is not your problem. Your board is.

Should I connect Claude to my tools so I don't paste? Later, maybe. First, paste. You need to see the lie with your own eyes. Connectors make the lie faster. When the Monday output has been useful for a month and you are sick of CSV, then look at a scheduled dump. The thought pattern is the point, not the logo on the scheduler.

What if the five accounts are all unpaid invoices? Then that's the week. Money is a health signal. Don't force a "wow" onto the page to make the brief feel balanced. Pay the coordinator to work the aging. Put a wow on the list when you actually have a delivery win.

Is a 3-star really "customer health"? It's Quality, public, with a name on your Google page. It's also Effectiveness, because the next stranger reads it. Treat it as a check-in, not a brand crisis. Make the person's visit right if you can. Don't beg them to change the star. Don't write a fake 5-star from the shop to bury it. We never fabricate reviews.

Screen-recording notes (8–12 min, lo-fi)

1. 0:00–0:50 — Camera. "When you add trucks or chairs, you lose the feel. Don't buy a dashboard. Dump last week."
2. 0:50–3:30 — Screen: a redacted CSV of jobs. Show the columns: completed, on time, callback, late part. Paste reviews and aging underneath. No fancy BI.
3. 3:30–6:30 — Paste the weekly prompt. Scroll the output. Cross out a invented score out loud. Circle three names that match real rows.
4. 6:30–8:30 — One-pager prompt. Five accounts. Kill a sixth. Read the executive summary.
5. 8:30–10:30 — Outreach prompt. One apology draft. You rewrite a discount the model offered. Label HUMAN SENDS. Do not click send on camera unless it's a dummy draft.
6. 10:30–end — "Monday, 45 minutes. Want this installed? free Mini Margin Check or $1,500 Margin Scan. No free audit."