AI + human customer conversations, answered in Microsoft Teams.
Point of Contact puts an AI + human support team on your website and inside Microsoft Teams — and the AI always runs on Azure AI you own, billed to you by Microsoft, on every plan we sell.
Built on Microsoft Teams and Azure
Microsoft Teams Entry price
From $39/month
14-day free trial · Annual: two months free
Workspace
One Teams tab
Chat that lives where your team already works.
The AI
Your agents, your tokens
BYO Foundry, every plan
Volume
Unlimited AI conversations
No per-resolution fee
Fragmented widgets per domain, someone else's tokens, cold handoffs, and anonymous-or-nothing visitors — four ways external chat breaks before a person ever answers.
Your websites, portals and apps carry the widgets. Your team works in a Microsoft Teams personal tab. Between them sits the Point of Contact service, which we operate. Every prompt and completion is served by the Azure AI Foundry project you own, billed to you by Microsoft. Visitor sign-in goes through the Entra External ID tenant you own. Files registered users submit land in a private file space your team reviews from the conversation.
01 · Widgets
Give each website, brand or app its own branded widget — routing, sign-in, files and hours per widget — all from one Teams tab.
Every widget is managed in the same Teams tab: add widgets in bulk, apply settings from another widget, preview who gets a chat, and give a widget its own admins.
Each widget carries a list of allowed origins, and that list drives the Content-Security-Policy frame-ancestors header on the widget host, so a browser refuses to render the widget on a domain you did not list.
One script tag on the page. Which widget answers, and which domains may render it, follow from the widget you point that tag at.
The widget is mobile-first: it respects the host page's safe areas, follows the on-screen keyboard as it opens and closes, and behaves with the browser back button on Android.
02 · Routing
Per widget: AI-first or human-first start, the Foundry agent that answers first, the hand-off groups, overflow after a set time, hours and the fallback.
Routing is a per-widget setting: how a new chat starts (AI first or a Teams user first), which Foundry agent answers first, which groups are offered the hand-off, which groups take the overflow after N minutes, which hours profile and availability source decide when a person can be offered, and what the widget shows when nobody is available.
Hours, presence, fallback. Hours decide when a human can be offered; live presence decides who is notified; outside both, the widget shows your fallback contact.
Business hours decide when a human can be offered and never gate the AI; presence decides who is notified; the fallback contact is a labelled button carrying the phone number, mailbox or booking link you configure.
The handoff timers. An unanswered request for a person returns to the AI after 5 minutes, an unaccepted transfer returns to the original agent after 2, and a chat with no activity closes itself after 10 minutes.
03 · Hand-off
One tap on "Chat with a Human" asks your team for a person, in the same thread. Business hours or live Teams presence decide when it is offered.
The widget's "Chat with a Human" button, or the same words as a quick-reply chip, asks your team for a person; whoever takes the chat in Teams joins the same thread, with the conversation so far. Per widget, business hours, live Teams presence or both decide when it is offered, and presence filters who is notified. When nobody is available, the widget offers your fallback contact.
AI first or human first. Hand off as often as it takes. Start with AI or a Teams user; "Chat with a Human" brings your team in; transfer, hand back, reopen — one thread throughout.
What the visitor sees. AI answers stream in as they are written, with quick-reply chips to tap; the visitor can download a transcript of the conversation; and every visible string, colour and system message is configurable per widget.
05 · Registered users
Visitors register and sign in inside the widget, through your own Entra External ID tenant and the identity providers you set there.
Sign-in mode is a per-widget setting: anonymous, optional or required. A support portal can require it while the marketing site never mentions it.
The service validates the token's signature, issuer, audience, tenant and object id before a session becomes an identified one; we store the object id, never credentials.
Past conversations. Signed-in customers open Past conversations inside the widget — their earlier chats, readable in full, with a PDF transcript to download.
Inside the widget, customers and partners get answers, tap "Chat with a Human", sign in, submit files and open Past conversations — without leaving your site.
06 · Files
Registered users upload, draft and submit files into a private Azure Blob space your team reviews from the same conversation.
Deletion goes through your team. A registered user can ask for a submitted file to be deleted; your team deletes it or declines with a reason, from the same conversation in Teams.
15 MB per file by default, 100 files and 500 MB per registered user, with the allowed file types set per widget; submitted files are kept in a 28-day backup.
Where a registered user can upload a file, it goes to a private Azure Blob space for your team to review. The AI never reads it.
07 · Analysis
An AI pass over closed conversations — by date, agent and domain — surfaces top topics and suggested improvements for AI and team.
Topic Analysis runs across your closed chats for the range you pick, groups them by topic, shows the domains behind each, and writes per-topic recommendations for your human agents and your AI agent. The closed-chat report adds source domain, agents, transfers and handling time. For continuous improvement: no sentiment scores, no trend charts, no per-user profiles.
Filter by date, agent and widget domain; each run classifies up to 200 new closed chats and reuses the classifications it already has, so a large backlog is worked through in predictable, priced steps.
The numbers behind closed chats
A read-only view of closed conversations, filtered by date, agent type, specific agent and source domain: chats resolved, time to resolution, human handling time, transfers per chat and who closed each one.
Agents and admins work in one Teams personal tab — take, transfer, close, review files, run analysis, change settings — with Teams SSO and activity-feed alerts.
No second console. Human agents claim, transfer, take over, reopen and close chats in a Teams personal tab; admins manage widgets, Foundry agents, groups, hours, sign-in, files and analysis in the same tab. Sign-in is Teams SSO; new chats, human requests, transfers and file submissions arrive as Teams activity-feed alerts, filtered by each agent's live presence.
Tell the Assistant what you want — "create a widget for acme.com" — and it changes the settings through the app's own endpoints, as you.
Helpdesk suites and Teams "bridges" push a notification into Teams; the work still happens in their console, on their tokens. Here the queue, the chat and the settings are the Teams tab.
Point of Contact 3 live chats Blue, next-day delivery
Damaged order, replacement
Quote documents submitted
Three published plans, from $39 a month with 3 seats; extra seats are metered, and Microsoft bills your inference.
$39/month
or $390 a year up front
3 seats included, +$20 per extra seat
3 agent seats, one website widget and unlimited AI triage, on a Foundry project you own.
$99/month
or $990 a year up front
7 seats included, +$18 per extra seat
7 seats, widgets on every domain, visitor sign-in and file spaces. Your model, always.
$199/month
or $1,990 a year up front
15 seats included, +$15 per extra seat
15 seats, Topic Analysis over closed chats, and 24/7 support with a named CSM.
Start includes one website widget on one domain. Growth adds widgets on any number of domains, visitor sign-in and file spaces; Professional adds Topic Analysis. Extra seats bill on the plan you picked, so compare at your seat count: 6 seats on Start cost $99, the same as Growth; 13 seats on Growth cost $207, more than Professional at $199.
Coming to the Azure Marketplace. Prices in US dollars.
None of the 14 chat and contact-centre products we compared in October 2026 combines all three: an agent workspace inside a Microsoft Teams tab, a website widget per domain, and hand-off from AI to a person and back again. Among the products that put agents in a Microsoft Teams tab, none documents a way to hand the conversation back to the AI. The comparison and its sources are published; tell us if we missed one and we will update it.
The leading AI helpdesks bill about a dollar per AI resolution on their model. Point of Contact bills per human seat; the AI runs on Foundry you own, and Microsoft bills the tokens at Microsoft's rates.
Microsoft retired Live Chat for Teams — new setups closed 6 August 2026; the service ended 5 October 2026, and embedded widgets are hidden. Point of Contact keeps the website widget answered by people in a Teams tab, and adds AI first and Foundry agents you own on every plan, plus more than one domain, registration and files from Growth.
Still have questions?
Get in touchA 20-minute call: your domains, your Teams setup, your Foundry — and which plan fits.
Email us directly
info@innovations24.comResponse time
We reply within one business day.
Status
Coming to the Azure Marketplace