Customer Support and Voice AI
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.
Front Line
AI Customer Support Agent for Salesforce Service Cloud
Service Cloud cases answered from Salesforce Knowledge, with the customer's entitlement checked before any action is taken.
Service Cloud holds everything an agent needs, but finding the right article and checking each customer's entitlement takes time on every case. This edition answers incoming cases from your Salesforce Knowledge articles, checks the contact's entitlement before acting, updates case fields and status within your rules, and routes the rest to the right queue with a case comment.
- Routine cases answered from your Salesforce Knowledge articles
- Entitlements checked before any action is taken
- Other cases routed to the right queue with a comment
$7,900
20–30 working days
Optional maintenance $395/mo
What it is
AI Customer Support Agent for Salesforce Service Cloud answers incoming cases from your Salesforce Knowledge articles, reads the contact and their entitlement to see what support they are owed, updates case fields and status within your rules, and routes the rest to the right queue with a case comment. Nothing changes outside your rules.
Why businesses buy it
Large support teams on Salesforce often have excellent knowledge content and strict service agreements, yet agents still resolve routine cases by hand. That keeps handle times high and makes it harder to meet entitlement targets. This edition resolves the routine cases consistently, respects each customer's entitlement and keeps case data clean for reporting. The scope names the case types, fields, queues and rules before you order, and it runs inside your own Salesforce org, so your admins stay in control.
Problems this solves
Cases sit in a general queue before anyone checks entitlement
The agent reads the contact and their entitlement to see what support they are owed. It answers or routes each case accordingly, so priority customers are not left waiting.
Agents look up the same Knowledge articles for every case
Incoming cases are answered from your Salesforce Knowledge articles and up to 100 approved documents. Routine cases close inside Service Cloud without an agent searching.
Case fields and status are updated late or not at all
Within your rules, the agent updates agreed case fields and status. The rest go to the right queue with a case comment, and nothing changes outside your rules.
A good fit if
Your support team works cases in Salesforce Service Cloud, and a large share are questions your Knowledge articles already answer.
Customers are on different support levels, and the answer or action depends on what their entitlement covers.
You want case status, reason and closure recorded properly so Service Cloud reports reflect what actually happened.
Your Salesforce admin can set up a connected app with a Service Cloud user and join a 30-minute setup call.
Not the right fit if
You only want new cases sorted into the right queue. See AI Ticket Routing for Salesforce Service Cloud.
You want account health scored on Salesforce accounts, not cases resolved. See AI Customer Health Score for Salesforce.
You want reply drafts and suggested articles for your agents rather than direct answers. See AI Support Copilot.
Your service team runs on HubSpot rather than Salesforce. See AI Customer Support Agent for HubSpot Service Hub.
How it works
- On a 30-minute call your Salesforce admin agrees the field mapping: which case fields, contact data, Knowledge articles and entitlement details are read or updated.
- Your Salesforce Knowledge articles, plus approved FAQs and policies, become its knowledge, up to 100 documents.
- Each new case on the chosen channel is read with the contact and their entitlement, so the reply and any action match the support level they are owed.
- Within up to six workflows it updates case fields, adds the reply and closes cases that meet your criteria.
- Cases outside its confidence, or above the customer's entitlement, go to the queue your escalation rules name with a case comment summarizing what was asked.
- Fifty scenarios built from your past cases are tested in a sandbox or on test records before launch.
What you provide within 72 hours
Your portal lists these the moment you order. Delivery starts the working day after everything is in and your access is checked.
- A Salesforce connected app with a Service Cloud user.
- A Salesforce admin for a 30-minute setup call, and sandbox access if you have one.
- Your Knowledge articles, FAQs and support policies.
- How your entitlements map to what each support level may receive.
- Escalation rules, queues and support hours.
- Ten real cases showing typical questions, the approver for actions, and access to any second system.
- One decision-maker for sign-off; credentials are never sent by email.
- A rough count of your current help articles, FAQs and saved replies, so we can check there is enough source content to answer from.
- An API key for your own AI model account (for example OpenAI or Google Gemini), created for this build with a spending limit.
The 72-hour rule. Send everything on your checklist, including access, within 72 hours of ordering so your build starts on time.
Timeline
Start
Intake verified, connected app tested, case and entitlement mapping agreed.
Weeks 1–2
Knowledge articles loaded; case reply workflows built.
Week 3
Entitlement checks, case updates and queue handoffs connected.
Weeks 3–4
50 case scenarios tested in sandbox or on test records.
Week 4
Review with your admin and two rounds of changes.
Go-live
Live in Service Cloud, recorded handoff, support begins.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $7,900 |
| Express | 15–25 working days | $8,900 |
| Rush | 10–20 working days | $9,900 |
What you receive at handover
- The support agent configured inside your Salesforce Service Cloud org on one agreed channel
- Two-way Service Cloud connection with documented field mapping, plus up to one more system
- Up to six workflows with your approval rules, including entitlement checks
- Access through user invites or keys you control, with no keys sent by email
- Test report from 50 scenarios on sandbox or test records
- Admin guide, recorded 60-minute handoff session and 30 days of post-launch support
Expected benefits and how to measure them
- Customers can receive support matched to their entitlement from the first reply.
- Agents can spend less time searching Knowledge for routine answers.
- Helps keep case data current for your Service Cloud reports.
- Cases closed by the agent
- Build a Salesforce report on cases closed by the agent's user. Compare weekly totals with overall case volume.
- Entitlement milestone breaches
- Report on missed entitlement milestones. Compare the month before launch with the month after.
- Average case handle time
- Compare average time from case creation to close for four weeks before and four weeks after launch.
Before you start: Save a Salesforce dashboard of case volume, milestone breaches and handle time for the month before work starts.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
The build price is paid once. Running it costs roughly $50 to $250 a month for AI model usage and hosting, billed in your own accounts, on top of your Salesforce licenses. Salesforce editions, licenses and API allowances remain part of your Salesforce contract.
Build and test usage is billed to your accounts too.
Ask about running costsCustom requirements
Custom objects, fields outside the agreed mapping, a second channel, a third system or separate logic per business unit need a written Change Quote. Add a note at checkout and we send it to you. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionKeep it running
After launch, monthly maintenance keeps the agent current as your Salesforce org changes. It covers monitoring, fixes, updates, a health report and change hours for things such as new Knowledge articles, entitlement changes or Salesforce release updates. It starts after the post-launch support period, bills monthly and can be cancelled any month. Unused hours do not roll over.
$395/mo (5% of the build price a month, includes 3 change hours)
Optional. Starts after the post-launch support period. Cancel any month.
How maintenance worksHow this compares
| Do it yourself with a SaaS tool | Hire a custom agency | Upmark Labs | |
|---|---|---|---|
| Price | A built-in AI option is often licensed per user or by usage | A Salesforce partner quotes by the day | Ours is one fixed price, shown on this page before you buy |
| Entitlements | May answer every customer the same way | Depends on the brief | Ours checks the customer's entitlement before acting |
| Testing | Switched on in production | An agency build depends on what was agreed | Ours is tested in sandbox or on test records first |
| Delivery | Needs admin build and tuning time | An agency usually takes several weeks, set per project | Ours has a fixed delivery time shown before you buy, with faster options |
Questions about this product
How does the agent use Service Cloud entitlements?
It reads the entitlement linked to the customer to see what support they are owed. A customer on a basic level might be pointed to a Knowledge article, while a premium customer's case is routed to a person sooner. You define those rules at intake, and nothing outside them is decided automatically.
Does it answer from Salesforce Knowledge articles?
Yes. Your Salesforce Knowledge articles are its main knowledge, alongside any FAQs and policies you approve, up to 100 documents in total. If a case asks about something those do not cover, it adds a case comment and sends the case to your queue rather than guessing.
What does our Salesforce admin configure for the Service Cloud connection?
A connected app with a Service Cloud user, scoped to cases, contacts, Knowledge articles and entitlements in the agreed mapping, plus 30 minutes for the setup call. Licenses and API allowances remain part of your Salesforce contract, and access is never shared by email.
What does AI Customer Support Agent for Salesforce Service Cloud cost?
The build price, with the express and rush options, is shown in the price and delivery panels on this page, so the full figure is clear before you buy. Running costs of roughly $50 to $250 a month are billed in your own accounts, separate from your Salesforce licenses.
Why does the Service Cloud edition cost more than other helpdesk editions?
Every integration edition is priced as the core build plus a fixed uplift for that integration, and the Salesforce Service Cloud uplift is higher than the one for most helpdesks. The scope is otherwise the same as the other helpdesk editions: one channel, up to 100 documents, up to six workflows and 50 test scenarios.
Which Service Cloud channel does it cover?
One channel, chosen at intake, typically email-to-case or web chat feeding cases. A second channel is available as a channel add-on bought with the build, or through a Change Quote afterwards, so each channel's replies can be tested before it goes live.
Guides on this topic
All guides Resolve routine cases inside Service Cloud, by entitlement.
Order the AI Customer Support Agent for Salesforce Service Cloud and resolve routine cases by entitlement, inside your org. Case types and queues are agreed in writing first.
Works well with
Support Operations
AI Ticket Routing
Routes tickets to the right team or agent based on content and skills.
Support Operations
AI Support Supervisor
Oversees AI and human support queues, SLAs and quality in one view.
Support Operations
AI Support Knowledge Agent
Finds gaps in your help center and drafts new articles from resolved tickets.