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 FAQ Agent
Website visitors get instant answers from your approved FAQ set, with anything outside it handed to a person, not guessed.
Visitors ask the same questions about hours, shipping, pricing and policies, and many leave if they cannot find an answer quickly. This agent answers them instantly on your website, Slack or Microsoft Teams, using only the FAQs and documents you approve. Anything outside that set goes to your escalation email or helpdesk, so nobody gets a guessed answer.
- Instant answers to your most common questions, at any hour
- Replies drawn only from FAQs and documents you approve
- Unanswered questions passed to your team, never guessed
$3,400
20–30 working days
Optional maintenance $249/mo
What it is
AI FAQ Agent answers frequently asked questions on your website, Slack or Microsoft Teams using only the FAQs and documents you approve, and hands off anything outside that set to your escalation email or helpdesk. It never invents an answer outside your approved content.
Why businesses buy it
Every question a visitor cannot answer is a chance for them to leave, and every repeated email takes time from your team. Most of those questions already have a written answer somewhere on your site. This agent puts those answers in front of people the moment they ask, in a friendly, consistent way, and it is tested against your own documented questions before launch. The scope names the channels, FAQ set and escalation route before you order, so you know exactly what it answers.
Problems this solves
Your team answers the same handful of questions every single day
The agent answers up to five common question types from the FAQs and documents you approve. It runs on your website, Slack or Microsoft Teams, so people get answers where they already are.
You worry a chatbot will make up answers
It answers only from approved content, up to 100 documents or 200 web pages. Anything outside that set goes to your escalation email or helpdesk instead of a guess.
Questions arrive outside office hours and wait until morning
Common questions are answered at any hour from your approved FAQs. The test report covers 40 documented questions with pass or fail results, so you see how it behaves first.
A good fit if
Most of your customer questions are the same handful you already answer in an FAQ page or a help center.
You don't need it to take actions like refunds or order changes, only to answer questions accurately.
You want a widget on your website, or a bot inside Slack or Microsoft Teams, not a full helpdesk rebuild.
You have your top 20 FAQs written down, or can write them, with answers your team already stands behind.
Not the right fit if
You need it to also take actions, such as issuing refunds or updating a customer record. See AI Customer Support Agent, which is built to act, not just answer.
Most questions are specifically about an order's status or delivery. See AI Order Support Agent, which is built around live order data.
Your questions usually need step-by-step technical troubleshooting, not a fixed FAQ answer. See AI Technical Support Agent, which is built for that.
You need more than 100 documents, more than five intents, or answers in more than one language. Add a note at checkout for a Change Quote, or use our Custom AI enquiry form.
How it works
- It learns only from what you approve. Your top 20 FAQs with their answers, plus up to 100 documents or 200 web pages, nothing invented outside that set.
- It sits on the one channel you choose. Your website widget, Slack or Microsoft Teams, matching your logo and brand colors from the first message.
- Visitor questions are matched to an intent. Up to five intents such as pricing, hours or how a feature works, each answered from the approved source, word for word where the FAQ already has the wording.
- A question outside its FAQ set hands off, not guesses. To the escalation email or helpdesk you connect, so nobody gets an invented answer.
- Every exchange is logged and testable. 40 documented test questions with pass or fail results delivered before launch, so you see exactly what it does and does not know.
- It only answers, it never changes a record. No refunds, no account edits, no order changes, for that, see AI Customer Support Agent or AI Order Support Agent.
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.
- The documents or website URLs the bot should learn from.
- Your top 20 FAQs, written with the answers your team already gives.
- An escalation email or helpdesk access for handing off anything outside the FAQ set.
- Website admin access, or your developer's help, to install the widget.
- Your logo and brand colors so the widget matches your site.
- Admin access and API keys for every connected system, shared by adding our team as a user or creating a key you control, never by email.
- Your business information (company basics, hours and brand voice), shared during intake.
- One decision-maker who can approve the final FAQ set.
- 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, FAQ set and documents confirmed.
Weeks 1–2
Knowledge base built and the widget or bot configured.
Week 3
Handoff integration connected and brand styling applied.
Weeks 3–4
40 documented test questions run with pass/fail results shared.
Week 4
Your review and two rounds of changes.
Go-live
Live, recorded handoff session, 30 days of support starts.
| Option | Delivery time | Price |
|---|---|---|
| Standard | 20–30 working days | $3,400 |
| Express | 15–25 working days | $4,000 |
| Rush | 10–20 working days | $4,600 |
What you receive at handover
- The FAQ agent configured and deployed on one channel: website widget, Slack or Microsoft Teams
- Prompt and guardrail configuration covering up to five intents plus human handoff
- Handoff connection to one system, such as your escalation email or helpdesk
- Test report with 40 documented questions and pass or fail results
- Admin guide and a recording of the 60-minute handoff session
- 30 days of post-launch support
Expected benefits and how to measure them
- Common questions can be answered instantly, at any hour.
- Your team can spend less time repeating the same answers.
- Makes it easier to spot gaps in your FAQs from what people ask.
- Questions answered without handoff
- Count conversations in the agent's log that ended without escalation. Track weekly totals after launch.
- Repeat questions reaching staff
- Tally the top five FAQ topics in your inbox or helpdesk. Compare four weeks before launch with four weeks after.
- Handoff topics
- Review handoffs each week by topic. Topics that recur may show where a new FAQ is needed.
Before you start: For two weeks, tally how often your top five FAQ topics reach your team, and by which channel.
These are things to track, not promised results. Outcomes depend on your data, your team and your market.
Running costs
The build price is one-time. Running it costs roughly $30 to $150 a month in your own accounts for AI model usage and hosting, scaling with how many visitors ask it a question.
AI usage during the build and testing is billed the same way, in your own accounts, so every provider relationship stays yours.
Ask about running costsCustom requirements
If you need more than 100 documents, more than five intents, or FAQ answers in more than one language, add a note at checkout for a written Change Quote. Larger or bespoke projects go through the Custom AI request form instead.
Request a custom versionKeep it running
After launch, monthly maintenance keeps the build current as your business changes. It covers monitoring, fixes and change hours for things such as new FAQs or seasonal updates. Maintenance starts after the post-launch support period, bills monthly and can be cancelled any month. Unused hours do not roll over.
$249/mo (the minimum fee, includes 2 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 chatbot widget charges a monthly fee per conversation or seat | A web agency quotes a build fee after discovery | Ours is one fixed price, shown on this page before you buy |
| Scope | A chatbot widget answers from whatever you upload, unchecked | An agency agrees scope during the project | Ours is written on the Scope Card, up to five intents |
| Delivery | A chatbot widget installs same-day but needs content written for it | An agency usually takes several weeks, set per project | Ours has a fixed delivery time shown before you buy, with faster options |
| Accuracy | A chatbot widget can improvise when it doesn't know | An agency build depends on what was agreed | Ours answers only from your approved FAQs, tested on 40 questions |
Questions about this product
Does AI FAQ Agent make up an answer if it doesn't know?
No. It only answers from the FAQs and documents you approve. If a question falls outside that set, it says so directly and hands off to your escalation email or helpdesk, rather than guessing. That boundary is tested against 40 documented questions before launch.
What does AI FAQ Agent cost to run each month?
Roughly $30 to $150 a month in your own accounts for AI model usage and hosting, scaling with how many visitors ask it something. You pay this directly to the provider. Monthly maintenance is optional. We charge nothing per conversation.
How fast can AI FAQ Agent go live?
Delivery follows the fixed timeline shown in the delivery panel, counted from a verified intake. Express and rush options are available for a fee. The clock starts once your FAQs, documents and website access are confirmed, so gathering your best existing answers early keeps the build on schedule.
Can it take actions like refunds or order changes?
No, it only answers questions from your approved FAQ set; it never edits a record or issues a refund. If you need it to also take actions inside your rules, see AI Customer Support Agent, which is built specifically to act as well as answer.
Where can visitors reach it?
On the one channel you choose: a widget on your website, or a bot inside Slack or Microsoft Teams. It matches your logo and brand colors from the first message, and any question outside its FAQ set hands off through the one connected integration you set up.
Can I add more FAQs or a second channel later?
Yes. Adding new FAQs or updating an existing answer fits inside the monthly change hours included with maintenance. A second channel, more than 100 documents, or answers in more than one language is scoped and quoted separately as a Change Quote.
What if it answers a question incorrectly at launch?
You get two rounds of changes built into the build price, using the 40 documented test questions it was checked against. After delivery you have five working days to flag anything that doesn't match the Scope Card, fixed as part of the original price.
Who owns the FAQ content and conversation logs?
You do. Your FAQ set, the documents it learned from and every logged conversation belong to your business. There is no license fee for keeping the bot live after launch, only optional monthly maintenance if you want ongoing FAQ updates made for you.
Guides on this topic
All guides Answer the same questions once, not every time.
Order the AI FAQ Agent and answer your most common questions once, for every visitor. Channels, FAQ set and escalation route are agreed in writing before you pay.
Works well with
Front Line
AI Order Support Agent for Gorgias
Answers order status, delivery and change requests using live order data, connected natively to Gorgias so it reads and updates tickets, customers,…
Front Line
AI Order Support Agent for BigCommerce
Answers order status, delivery and change requests using live order data, connected natively to BigCommerce so it reads and updates orders, shipments…
Front Line
AI Order Support Agent for Adobe Commerce
Answers order status, delivery and change requests using live order data, connected natively to Adobe Commerce so it reads and updates orders,…