Every new capability, integration and improvement, written by the team, newest first. Your AI employees pick these skills up automatically; no retraining, no upgrade projects.
July 2026
FeatureJul 2
Invoice billing for enterprise (net terms)
Enterprise customers can now be set up on invoice billing with net payment terms instead of an upfront card charge. The Quincer team provisions your subscription on your organization's own billing account; Stripe issues an invoice in your company's name, due within your agreed net window (e.g. net-30), and your workspace is activated immediately. No card required. The invoice is a normal Stripe invoice you can view and pay from manage-billing. This is arranged by our team for enterprise accounts; contact us to set it up.
You can now choose which persona handles each connected Facebook Page, Instagram account, and WhatsApp number, right from Integrations → the connection's Account tab. Run a playful, on-brand persona on Instagram and a buttoned-up one on Facebook, each with its own system prompt and tools. The assigned persona answers that channel's comments and DMs; leave it on "Widget default" and nothing changes. Find it under Integrations once a Meta channel is connected.
Privacy controls: automatic data retention & deletion
You can now control how long Quincer keeps personal data and respond to data requests, all under Settings → Privacy. Set an automatic deletion window per data type (visitor memory, chat & voice transcripts, voicemail recordings, leads, surveys, and inbox email) and Quincer deletes anything past that window daily (files included). Need to handle a data-subject request? Look up, export, or permanently erase everything held about one person (by email, phone, or visitor ID) across every store. Every deletion is logged for your compliance records.
Check your phone line, and never get caught out of minutes
Telephony just got easier to trust. Each mapped number now has a "Check setup" button that reads your Twilio configuration and confirms the call webhook points at Quincer (with the exact fix if it doesn't), plus a "last call received" status so you can see at a glance whether calls are reaching you and connecting. And if your voice minutes run low or run out, a banner now warns you in the dashboard, instead of a caller being the first to find out.
Persona Workflows: describe your process in plain English
Each persona now has a Workflows field: write, in plain English, the step-by-step process it should follow for specific situations, and which tools to use. For example: "When a lead is captured with their company and email, look the company up on Apollo, and if they're a strong fit offer to book a meeting and update the CRM." A tool palette shows exactly which of your connected tools that persona can use, and workflows apply everywhere the persona acts: chat, social replies, and email. The System prompt is who the persona is; Workflows are how it works.
Workflow triggers: tie each persona workflow to a specific event
Persona workflows now have triggers. Pick the event each workflow runs on: a new chat, a new lead, a new social comment, a new direct message (WhatsApp / Messenger / Instagram), an inbound email, or the follow-up email after a chat. You can also define your own trigger in plain English. A workflow only runs on its event's channel, so a social-comment workflow never clutters a web-chat reply. The Workflows section is collapsible and shows how many are active at a glance; expand it to add, edit, or remove them, with one-click AI review on each.
Review & refine: let AI tighten up your persona workflows
Writing a workflow for a persona? Click "Review & refine" and the AI checks it for clarity, missing steps, and vague conditions. And because it knows which tools that persona has connected, it flags any step that names a tool you haven't set up (and suggests one you have). It proposes a cleaned-up version you can accept with one click or ignore. Nothing changes unless you apply it.
Sentiment escalation: auto-flag conversations that turn negative
Your assistant now watches conversation sentiment and escalates the ones going sideways. When a visitor sends several negative messages in a row, the conversation is automatically routed to a human: flagged on the Live Conversations dashboard, or posted to your Slack, Teams, or Telegram escalation channel with a Take over button. Set the negative-streak threshold and a cooldown per persona under Persona → Channels → Sentiment escalation. Requires sentiment scoring (Analytics → Sentiment). Scale plan.
Turn on Sentiment scoring (Analytics → Sentiment) and Quincer classifies every visitor message (positive, negative, a question, or neutral) and rolls it up per conversation. The new Sentiment tab shows your message-sentiment mix, average sentiment over time, and a "Needs attention" list of the conversations with the longest run of negative messages, so you can jump on a frustrated visitor. It runs on the lightweight utility model, off the chat's critical path, and is off by default.
Your Analytics → Feedback tab now gives the full CSAT picture: average rating, resolution rate, and (new) your response rate (how many conversations actually left feedback) plus a responses-over-time trend and a per-persona breakdown. Averages built from only a handful of ratings are flagged as directional so a couple of responses never mislead you. Turn on the CSAT survey from that tab to start collecting it.
Monthly Performance Report: your AI's ROI, in your inbox
On the 1st of each month, every brand now gets its own executive performance report by email (one per brand, not a blurred org-wide average) covering conversations handled, resolution rate, median first response, CX score, a 6-month trajectory, and an estimated support cost saved with every assumption shown. The ROI is deliberately conservative (it only counts resolved chats that would have reached a human), so it holds up to a finance review. It also surfaces the top content gaps worth closing and recommended next moves. Tune the cost assumptions and preview last month's report under Settings → Reports.
Plug any remote MCP (Model Context Protocol) server into Quincer (your own, or a vendor's hosted server like Jira or GitHub) and your AI personas instantly gain its tools, even for apps we don't integrate directly. Paste the server URL and an access token, pick which actions to enable, and they work right alongside your built-in integrations. Manage servers under Integrations → MCP servers.
Keep the phone numbers your customers already know (including several toll-free lines) and have an AI persona answer them, without porting. Forward your numbers to your Quincer number (or point a bring-your-own-carrier trunk at it) and we route each call by the number the caller actually dialed, so every line can map to its own persona. Set it up on the new Phone numbers page.
Callers can now text your phone number and get an instant reply from the same AI persona, with your knowledge, booking links, and follow-up. Incoming texts are free; outbound replies draw from your voice plan's included SMS. Turn it on with the "Text things to callers" toggle in Telephony.
Prefer to run on your own carrier? Connect your Twilio or Telnyx account per widget and your AI answers calls and sends texts from your own number. We just provide the agent. Paste your credentials in Telephony; in-app instructions show the exact webhooks to set.
When a caller asks for a person (or presses 0), your AI now warm-transfers the live call to a real teammate or number, ringing their phone and bridging the call. Set each persona's handoff target on its page (a teammate, or a number); add teammates' phone numbers on the Team page. If nobody answers, the caller leaves a voicemail that's emailed to your team, then returns to the AI so they're never stuck.
Your AI now greets phone callers the moment they connect. We pre-render each persona's phone greeting in its exact AI voice and language and play it the instant a call is answered, so callers hear a warm welcome with no awkward silence while the assistant spins up. It's fully automatic; nothing to set up.
When Subject Memory is on, your assistant now recognises returning phone callers by their mobile caller ID. No sign-in needed. It knows whether someone is calling for the first time or again, remembers what they discussed on previous calls (and a name they gave), and greets a returning caller warmly. If a call gets cut off, the next call can pick up where they left off. Landlines aren't tracked, and you can review or delete any caller's memory from the dashboard.
Visitor & team memory: your assistant now remembers people
With Subject Memory on, your assistant recognizes returning signed-in visitors, greeting them by name, recalling what they asked about last time, and skipping questions they've already answered. It also remembers social commenters, and gives the dashboard Pilot recall of your team's recent changes. Off by default, opt-in per widget, verified-identity only, with per-person export and delete (GDPR).
Microsoft Teams: bring your AI assistant into your channels
Connect Quincer AI to Microsoft Teams so your assistant can answer questions and hand off to humans right inside your team's channels and 1:1 chats, with per-persona channel routing and a dedicated history channel.
Store locators & service-area maps, right in the chat
Ask "where's your nearest location?" and your assistant now answers with an interactive map in the chat canvas: store locators, service areas, bus stops, and more. Locations are auto-detected from your knowledge base (or imported by CSV), with a free map by default and an optional Google Maps key.
Rich product & info panels inside the conversation
Generative UI lets your assistant render polished, on-brand panels in the chat (product grids with prices and add-to-cart, step-by-step guides, pricing tables, and curated info pages) instead of plain text. Grounded in your knowledge base and your brand theme.
Cart-aware chat for Shopify: add to cart in conversation
On Shopify stores, your assistant can now read the visitor's live cart and add products during the conversation, including variant selection and abandoned-cart nudges. Opt-in under Customize → Capabilities.
Quincer AI for Shopify: one-click install, billing & live catalog
Install from the Shopify App Store and the widget embeds on your storefront automatically. No code. Native Shopify billing, a purpose-built commerce persona, and live product-catalog sync so the assistant always knows your current products and prices.
React Native SDK: add Quincer AI to your mobile app
A native React Native SDK brings the full widget (chat, voice, identity, and transcripts) to your iOS and Android apps, with the same configuration you already use on the web.
Your assistant now detects the visitor's language and replies in it (across chat, voice, the canvas, and the greeting) so you can serve a global audience without configuring anything.
Connect Gmail or Outlook and your assistant sends lead follow-ups from your real address (with Gmail send-as support), under your control. Per-brand lead notification emails and a dedicated Email Configuration tab keep every brand's outreach on-brand.
Build your knowledge base by crawling your website
Point Quincer AI at your site and it crawls and imports your pages into the knowledge base, with a one-click Recrawl to stay current. Search is now far faster on large knowledge bases (tens of thousands of items).
Custom Tools: connect any REST API to your assistant
Give your assistant new abilities by connecting your own REST APIs as tools. No code on our side. Part of a redesigned Integrations dashboard that makes connecting Slack, HubSpot, Calendly, Google, and more far clearer.
Pilot: in-product help and brand-activity insights
Pilot, your in-dashboard assistant, now answers "what did my assistant do this week?" with real numbers (conversations handled, leads captured, meetings booked, emails and social replies, voice calls) per brand. It also helps you troubleshoot and can open a support ticket when needed.
Your monthly Quincer AI email now includes a personalized recap of what your assistant accomplished across your brands (conversations, leads, meetings, emails, social replies, and voice) so you can see the value at a glance.
Shopify merchants now have a dedicated page with cart-recovery and wholesale-qualification flows, plus a Shopify-specific comparison table and pricing guide. Existing pricing; same trial.
Perplexity Computer: drive live chats and leads in plain English
Connect Perplexity Computer to your Quincer AI workspace in one click. You'll get a dedicated 'Perplexity Computer' agent, a scoped API key, and a downloadable SKILL.md so Perplexity can read transcripts, take over live conversations, reply as a human agent, hand back to the AI, and update leads, all from natural-language prompts like 'show me today's hot leads' or 'reply to the visitor asking about pricing'.
Pick OpenAI Realtime (ten voices including marin and cedar) or stay on xAI Grok. Switch per-workspace in Settings → Voice; each persona can pick any voice from either provider, and we warn you if the selection doesn't match your workspace's active provider.
Voice chat now supports Google Gemini Live alongside xAI and OpenAI. Eight prebuilt voices (Aoede, Charon, Fenrir, Kore, Leda, Orus, Puck, Zephyr) and native support for 70+ languages, a strong pick when you need multilingual delivery. Switch per-workspace in Settings → Voice.
Visitors can talk to your voice agent in their preferred language and get responses back in the same language. No cascading speech-to-text / translation / text-to-speech pipeline, no extra latency. Configure supported languages, set a default, and turn on auto-detect in Widget → Customize → AI agent. English, Spanish, French, German, Japanese, Arabic, Hindi, Mandarin, and more.
Choose how voice calls appear in the widget: Hybrid (default), Takeover, Inline, or Strip. The Appearance tab now shows a live preview of each layout, and a Try voice live button iframes the real widget with a Desktop/Mobile toggle so you can test before visitors see it.
Audition any of the 15 voices before choosing one. A Preview button on the persona voice dropdown plays a short sample so you can compare tone and cadence across xAI and OpenAI voices side by side.
Every voice turn now searches your knowledge base (the same cross-persona vector search text chat uses) and injects the matches into the model's context before it speaks. One KB, two channels, identical grounding. No more voice agents inventing product facts.
Connect your agency-focused CRM and give the agent a rich toolset: create contacts and opportunities, book calendar appointments, log conversation messages, and open support tickets. Changes in the CRM flow back into Quincer AI leads via webhooks so contact updates, new opportunities, and appointments stay in sync automatically.
Ask Perplexity Computer to show your hot leads, take over a live chat, or update lead stage, in plain English. Actions are attributed to a dedicated Perplexity team-member identity in your Quincer AI inbox, so you get a full audit trail instead of anonymous bot activity.
Social channels (preview): Facebook, Instagram, WhatsApp
Foundation shipped: connect a Facebook Page, Instagram Business account, or WhatsApp Business number from Integrations and the AI starts handling DMs and comments using your knowledge base. Sign in with Facebook is now also an option on the login screen alongside Google and Microsoft. Full per-channel features (templates, comment moderation, public→DM bridge, WhatsApp meeting booking) ship over the next few releases.
Invite others to Quincer AI and earn 20% recurring commission for their first 12 months. Grab your unique link from Dashboard → Affiliates, track clicks and conversions in the partner portal, and get paid monthly via Stripe Connect.
Slack: proactive pings, /quincer live, and a dedicated Live Chats channel
Slack gets a major upgrade: per-persona toggles for new-conversation and qualified-lead pings so you can jump in before the AI escalates, a /quincer live command that lists active chats with one-click Take over, and a new Live Chats channel setting that keeps proactive activity out of your escalation channel. Also shipped: /quincer leads, /quincer lead <email>, /quincer stats, and DM query support. Docs now recommend a clean 3-channel setup (history, escalation, live) so signals don't drown each other out.
Voice now has real billing. Buy minute bundles (60/180/960, monthly or one-time) or bring your own xAI key on our flat-fee BYOK plan for unlimited minutes. New /dashboard/billing/voice page to manage bundles, 80%-usage email warnings, and per-widget voice-enable toggle so agency owners can turn voice on only where it makes sense.
Visitors can switch from text to voice with a single click. Headphone chip in every widget's header, lazy-loaded voice module, xAI Grok voices (Eve default), real-time barge-in, silence + max-length protection. Bring your own xAI key. We proxy through a secure relay so keys never touch the browser.
Comprehensive product documentation is now live: quickstart, install guides (Shopify, WordPress, Webflow, custom sites), configuration walkthroughs, integrations, and API reference. Linked from the dashboard and footer.
Your AI agent can now search your Drive, share files with visitors, and attach documents to email follow-ups, all with a Google account picker during setup.
Connect a dedicated Gmail or Microsoft 365 inbox to each persona. Quincer AI monitors incoming mail, drafts context-aware replies, and threads conversations automatically.
A redesigned analytics page tracks conversations, leads, meetings booked, and per-widget AI cost so you can see the full funnel at a glance.
FeatureApr 9
Visitor file uploads
Visitors can now attach files in chat, useful for support tickets, quote requests, and lead-capture flows that need supporting documents.
ImprovementApr 9
Notification preferences and one-click unsubscribe
A new notifications tab in settings lets every user opt in or out of announcements and monthly updates, with a one-click unsubscribe link in every email.
FeatureApr 6
Groq LLM provider with free tier model
Add Groq as an LLM provider and choose gpt-oss-20b as a zero-cost option for Free-plan widgets: instant, high-throughput responses out of the box.
FeatureApr 6
Shopify Theme App Extension
One-click install for Shopify merchants: activate the widget directly from the Shopify theme editor with a deep link from your dashboard.
A new website-first onboarding flow detects Shopify stores, auto-crawls your content into the knowledge base, and creates an API key so the preview works immediately.
FeatureApr 5
Scheduled knowledge sync and live URL fetch
Per-persona sync schedules keep your knowledge base fresh automatically, and volatile URLs are refetched on demand so answers never go stale.
A new proactive agent qualifies visitors against Budget, Authority, Need, and Timeline, scores them 0-100, and triggers the right follow-up automatically.