AI receptionist for small business: calls, bookings and handoffs
What an AI receptionist does on a real call, the rules that apply, a sample greeting and a pass/fail checklist to launch one safely.
A health score on every Salesforce account, with a task created for the owner when the score drops sharply.
If account health lives in a side spreadsheet, it is out of date by Friday. This edition reads Salesforce accounts, opportunities, cases and activity, adds one more source such as billing or usage, and writes a health score to the account fields you agree. When health drops sharply, the account owner gets a Salesforce task, so action starts where your team already works.

AI Customer Health Score for Salesforce reads accounts, contacts, opportunities, tasks and activity history through a connected app, adds one more system such as billing or usage data, and writes a health score to mapped account fields. Sharp drops can open a Salesforce task for the account owner. Sharp drops can open a task automatically.
Salesforce holds most of what you know about a customer, but not usage or billing, and not in a form anyone can scan quickly. Teams end up building health scores in spreadsheets that are stale within a week. This edition puts a tested score directly on the account and creates a task when it drops, so risk turns into action. The documented field mapping and written scope set out what is read, what is written and how it is tested.
The score is written to mapped Salesforce account fields through a connected app. Owners see it on the account page and can use it in list views and reports.
It reads accounts, contacts, opportunities, tasks and activity history, then adds one more system such as billing or usage data. Both feed a single health score.
A sharp fall can open a Salesforce task for the account owner automatically. Up to five alerts also go to email, Slack or a web dashboard.
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $5,000 |
| Express | 15–25 working days | $5,750 |
| Rush | 10–20 working days | $6,500 |
Before you start: Pull last year's renewal opportunities and outcomes from Salesforce. Note how owners currently flag risk.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
You pay once for the build. Running costs are roughly $20 to $150 a month for AI model usage and hosting or scheduling, billed in your own accounts. Salesforce licenses, API limits on your edition and any upgrades stay with your Salesforce contract and sit outside this build.
Build and test usage is charged to your accounts too.
Ask about running costsCustom objects, fields outside the agreed mapping, more than one extra system, or scores per opportunity rather than per account need a Change Quote. Note it at checkout for a written quote. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionMonthly maintenance for this edition covers monitoring, fixes, updates, a health report and change hours, enough for new account fields, revised weightings and Salesforce release changes. The hours scale with your build.
$250/mo (5% of the build price a month, includes 2 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance works| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | A CS platform adds per-seat fees on top of Salesforce | A Salesforce consultancy quotes by the day | Ours is one fixed price, shown before you buy |
| Where health shows | In a separate app synced back in | Depends on the brief | Ours writes to account fields and creates owner tasks |
| Testing | Turned on in production | An agency build depends on what was agreed | Ours is tested on sandbox or test records first |
| Delivery | A managed package needs admin setup time | An agency usually takes several weeks, set per project | Ours has a fixed delivery time shown before you buy, with faster options |
Leads, contacts, accounts, opportunities, tasks and activity history, through a two-way connection. The score itself is written to the account fields agreed in the documented mapping. Custom objects and fields outside that mapping are not touched unless added through a Change Quote.
Yes. Up to five alerts are included, and each can create a Salesforce task assigned to the account owner when health falls past the threshold you set. The task carries the signals that moved, so the owner knows why it was raised before opening the account.
A sandbox is preferred but not required. Write-back is tested on sandbox or test records before launch, and you receive a test report. If you have no sandbox, a small set of agreed test accounts in production can be used instead, with your admin's approval.
Salesforce orgs change often: new fields, page layouts, validation rules and seasonal releases. Monthly maintenance includes change hours that keep the field mapping and the weighting current, and the hours scale with your build. Bigger changes go through a Change Quote. You can cancel in any month.
Each delivery speed has one fixed price. The price panel shows standard, express and rush side by side before you pay, and the cart confirms your delivery date. Running costs of roughly $20 to $150 a month are separate and paid to your own providers.
A connected app with an API-enabled user, scoped to the objects in the agreed mapping. Your admin joins a 30-minute call to agree which fields are read and written. Licenses and API allowances remain part of your Salesforce contract, and access is never shared by email.
Order AI Customer Health Score for Salesforce and each account carries a back-tested health score in Salesforce, with owner tasks opened automatically the moment health drops.

Predicts churn risk and recommends the retention play for each at-risk account.

Monitors accounts, runs success playbooks and prepares CSM actions.
