Skip to content

From October 1, WhatsApp charges for every business reply. Read the migration playbook

Changelog

What's new in SuperCognit

Everything we ship, written the way we'd explain it to a customer β€” new features, improvements and the occasional rename. Newest first.

Or follow the blog’s RSS feed

October 2026

A Feedback page, with an AI report

Every πŸ‘/πŸ‘Ž across your agents now has a page of its own. See how satisfied visitors are, go through each vote, and let an AI report tell you what to fix first.

  • Feedback in the main menu, with a badge that counts the πŸ‘Ž nobody has looked at yet.
  • Overview, for 7, 30 or 90 days: satisfaction and how it changed, thumbs down, comments, vote rate, votes per day, the reasons behind each πŸ‘Ž and satisfaction per agent. Click a reason, a day or an agent to see its votes.
  • Votes: the question, the reply, the sources it used and the visitor's comment, side by side. Search and filter, open the conversation at that exact reply, and mark each vote New, Reviewed or Fixed.
  • AI report (Starter and up): the problems visitors raised in the last 30 days, ranked by how many people raised them, quoted in their own words, each with a suggested fix you can copy into the agent's instructions, knowledge or tools. Plus what visitors liked.
  • Suggest a fix (Pro and up) on a single πŸ‘Ž: a proposed change for that one answer. Nothing is ever applied for you.
  • A comment written in another language gets a Translate link that puts it in yours.

Skills get their own page

Skills, the know-how an agent loads when a task calls for it, now sit on their own page next to Knowledge and Tools, and the agent editor has one tab for each.

  • Skills in the main menu: write a skill once, with its name, when to use it and the steps, then attach it to any agent or MCP server.
  • Every skill has a history, and can be duplicated or moved and copied to another workspace.
  • The agent editor's Intelligence menu is now Behavior, Capabilities, Knowledge, Skills, Tools, Media, Guardrails and Feedback. Capabilities gathers web search, memory, location and lead capture.
  • MCP servers get a Skills tab too.
  • Nothing changes for your agents: the skills they already use keep working exactly as before.

Archive contacts

Tidy up Contacts by archiving the people you no longer need to see, one at a time or many at once, and bring them back whenever you like.

  • Active and Archived tabs in Contacts.
  • Archive or restore from a contact's profile, or tick several rows, or all of them, and act on them at once. Undo is one click away.
  • Archiving only hides the contact from the list. Their conversations and subscriptions are untouched, and they can still sign in.
  • Also in the API and MCP: GET /v1/contacts and /v1/contacts/{email}, POST /v1/contacts/archive and /v1/contacts/restore, and the set_contact_archived platform tool.

Card details straight from your tools

The "More details" sheet on a card can now be filled by one of the agent's own tools instead of being written out by the AI, so answers with cards arrive faster.

  • Made for catalogues: book synopses, product specs, room descriptions. The agent shows the cards, and the details load only when a visitor opens one.
  • Works with the agent's read-only HTTP tools: the tool's answer supplies the details, images included.
  • Your content rules apply to these details just as they do to anything the agent writes.
  • On the chat page and in the widget.

See what the agent is doing while it works

When an agent looks something up before it answers, the chat no longer sits on a fixed "Thinking…". A short line says what it is doing right now, so visitors know the answer is on its way.

  • Live steps in place of "Thinking…": "Looking that up…", "Checking the documents…", "Browsing the website…", "Searching the web…", "Reviewing what I found…" and more.
  • If one step takes longer than 15 seconds, the line changes to "Still on it β€” this one takes a little longer…".
  • Steps describe the kind of work, never your tool names or what was sent to them.
  • On the chat page and in the widget, in all 14 languages.
  • Steps are only shown while the answer is prepared; they are not saved in the conversation.

Polish and Croatian

SuperCognit now speaks Polish and Croatian, everywhere: agents answer in them, and the chat, widget, channels, dashboard, emails and website are translated. Agents now work in 14 languages.

  • Polish and Croatian in the agent editor's language list, with their own translations of title, greeting and starter questions.
  • The chat page and the widget fully translated, including read-aloud and dictation voices.
  • WhatsApp and Telegram messages, refusals and queue notices in both languages.
  • The dashboard and every email to dashboard users in Polish and Croatian.
  • The website at /pl and /hr, with every page and every blog post. Visitors from Poland or Croatia, or with a Polish or Croatian browser, land there first; the language picker always wins.
  • Also in the MCP tools: pl and hr are accepted wherever a language code is.

Version history for agents, MCP servers and tools

Every change to an agent, an MCP server or a tool now leaves a version. Open History to see what changed, compare any two versions and restore one in a click.

  • A History tab under Setup in the agent and MCP server editors, and a history panel on every tool.
  • Each version shows who made the change and from where: the dashboard, the MCP, the API or an import. Quick saves in a row are grouped into one version.
  • Compare any version with another, or with what is live now.
  • Restore puts instructions, behaviour, widget look, welcome menus, translations, guardrails, feedback settings, attached tools, knowledge bases and videos back as they were. Price, access, team, custom domain and channels are never touched.
  • A restore is itself a new version, so it can be undone. After every Save an Undo button takes back your change.
  • Name a version as a checkpoint to keep it for good. How many other versions are kept depends on your plan.
  • If someone else changed the agent while you were editing, Save asks you to reload instead of overwriting their work.

πŸ‘/πŸ‘Ž feedback on answers

The πŸ‘/πŸ‘Ž buttons under every reply now reach you. You decide what each one asks, and the agent's Feedback tab shows what visitors said, with links to the conversations.

  • Per agent or MCP server, for πŸ‘ and πŸ‘Ž separately: open a short form or not, ask for a category (off, optional or required) and a comment (off, optional or required).
  • Up to 10 categories with a label per language. Five built-in ones, already translated into every chat language, are there to start with.
  • By default πŸ‘Ž asks what went wrong; πŸ‘ simply records the vote.
  • On the chat page and in the widget. The vote counts even if the visitor closes the form.
  • A summary of πŸ‘/πŸ‘Ž by category and the recent comments, each linked to its conversation; the Inbox shows every vote on its reply.
  • Also in the API and MCP: /v1/products/{id}/feedback-config, /feedback and /feedback/summary, and four platform tools to read and set feedback.

The whole answer in the Inbox

The Inbox now shows everything a reply showed the visitor, not just its text: the cards, the videos and what the agent did along the way.

  • Cards the agent showed, with title, subtitle, description, price and badge.
  • Videos the agent played, with their title and a link to watch them.
  • The knowledge sources a reply drew on, and the websites it found on a web search.
  • Payment links sent (amount and item), browser tasks started and verification codes sent, with the address masked.
  • A reply made only of cards or a video no longer shows as an empty bubble.

A calmer, quicker chat page

A round of polish on the chat page and widget: messages land where you can read them, phones get a composer at the bottom edge, and the sidebar tells you which chats are replying.

  • A sent message glides to the top of the view and the reply writes itself in below it, on the chat page and in the widget.
  • On phones the composer docks at the bottom edge, and a new chat opens with the greeting and starters centred above it.
  • A resizable sidebar on desktop; long chat titles slide to show their end on hover, and shimmer while their reply is being written.
  • Sidebar dots: pulsing while a chat is replying, green for a reply you have not seen. Switch to another chat and back, and "Thinking…" is still there until the reply lands.
  • Read aloud starts in about a second instead of waiting for the whole reply, and replays instantly.
  • A shorter disclaimer that fits in two lines, and a header that shows the agent's logo and name once the conversation has started.

Knowledge split into sections, and editable sources

Long, structured documents such as regulations and manuals can be split into sections at their headings, so the agent reads exactly the part it needs. And every knowledge source can now be edited in place.

  • Split into sections (beta): on pasted text and uploaded Markdown or Word files, with a live preview of the split and a short name for each document.
  • The agent sees the document's table of contents and reads the sections it needs, following references from one section to another.
  • A section count on each split source and a View sections panel to check the result.
  • Edit on every source: change the title and language, edit the stored text, or replace the file. A URL source can take a new address.
  • Agents keep answering from the old version until the new one is ready, so nothing goes missing mid-edit.

MCP servers that introduce themselves

When Claude, Gemini or any other MCP client connects to one of your MCP servers, it now sees the server's real name, a description and instructions on how to use it.

  • The client shows your MCP server's own title instead of a technical id.
  • A one-line description, a link to its info page and its icon, when you have set them.
  • Built-in instructions tell the client to search with the user's own words and answer only from what the tools return.
  • Only public details are shared; the private instructions you give the server stay on our side.
  • The SuperCognit platform MCP and the blog MCP now present themselves by name too.

Verify visitors by WhatsApp, SMS or email

Agents can now confirm who they are talking to on the chat page and in the widget: a mobile number or an email address, proved with a 6-digit code, before a tool acts on that person's data.

  • Three checks on the Tools tab, each with its own switch: verify by mobile number, verify by email, and verify by customer identifier (the code goes to the phone or email your own lookup tool finds on file).
  • Phone codes go by WhatsApp or by SMS, where available β€” one choice per agent under How codes are sent. The AI never sees the code.
  • Daily limits per agent and per number or address, so nobody can flood someone else's phone or inbox.
  • A phone the visitor already proved in the conversation verifies them as a customer without a second code.
  • The code box comes back after a reload, and shows βœ“ Verified once the code was used.
  • A redesigned Identity verification card that lists the tools using each check, and refuses to save a check that cannot work yet.

Finer control over WhatsApp

WhatsApp cost control is more precise, stays out of the way while a person answers, and the Channels tab is reorganised with a welcome menu per channel.

  • Answer for is now set in minutes, from 1 minute to 30 days.
  • A new limit, Answers per conversation: after that many answers the person gets the link to your web chat. Off by default.
  • While a teammate holds the conversation, or on an agent a person answers, cost control counts nothing and sends no link.
  • The link arrives as a "Continue on the web" button instead of a long address.
  • The Channels tab shows WhatsApp and Telegram as tiles, each with its own page and its own welcome menu.
  • Also in the API and MCP: windowMinutes and maxReplies on whatsappHandoff.

Small wins: chat backgrounds, domains, Portuguese and tools

A set of smaller improvements across the agent editor, from its own chat page background to a clearer custom domain status.

  • The chat page background is set on the General tab, and the widget can have its own Welcome cover image. Left empty, the widget keeps using the chat page image.
  • Custom domains show an honest status: each DNS record is checked live and marked in place or missing, the reason in plain words, root domains handled correctly, and a ⚠ Domain not connected badge on the agent card.
  • Agents that answer in Portuguese use European Portuguese by default, unless the person writes in Brazilian Portuguese.
  • New agents start with search-engine indexing off; turn it on when the agent is ready to be found. Existing agents keep their setting.
  • On the Tools tab, web search, memory, location, lead capture and identity verification are compact cards that open for details, and switches save at once.
  • HTTP tools handle large JSON responses better: the agent gets the whole structure, shortened to fit, instead of a cut-off answer.

A faster, roomier Inbox

The Inbox now updates the moment a message arrives, opens full screen, and has a reply editor that shows your formatting as you type.

  • Live updates: replies reach the visitor and new messages reach the Inbox in under a second.
  • A reply editor like Gmail's: bold, italic, links and lists you see as you write, with Ctrl+B, Ctrl+I and Ctrl+K. Enter sends, Shift+Enter starts a new line.
  • Full screen: the Inbox gets the whole window, the conversation list can be collapsed, and ← takes you back to where you were.
  • Resize the list and details panes, and choose short sounds for a new conversation, a visitor message or a teammate's reply.
  • A Settings cog for alerts, sounds and what each conversation card shows.
  • Filters fold into one button, view counts sit as badges on each view, and a Spam folder keeps junk conversations out of the way.

Photos, files and voice notes, both ways

Visitors can send photos, documents and voice notes, and your team can send files and voice notes back, on the chat page, the widget, WhatsApp and Telegram.

  • A record button on the chat page and in the widget, for voice notes of up to two minutes.
  • On agents a person answers, photos, documents and voice notes are kept and shown in the Inbox.
  • AI agents get voice notes transcribed, so they answer what was said.
  • From the Inbox, attach images, audio, PDFs and text files, or record a voice note; a reply can be files only.
  • Voice notes arrive as real voice messages on WhatsApp and Telegram, and play with a waveform player in the chat and the Inbox, at 1Γ—, 1.5Γ— or 2Γ—.
  • Also in the API and MCP: attachments on conversation messages, /v1/attachments/{id}, and files on replies.

Teams for hand-overs

Group your people into teams β€” sales, billing, support β€” and the agent hands each conversation to the right one, respecting each team's hours and how many chats a person can take.

  • Teams under Settings β†’ Teams, with members, opening hours, a backup team and a message for when the team is away. The old Team tab is now Members.
  • On the agent's Team tab, pick which teams it can hand over to; the AI chooses the right one from the conversation.
  • Outside a team's hours the conversation goes to its backup team, if that one is open.
  • A chat limit per person. When everyone is full, the visitor waits in line and is told their place ("#2 in line") and when they move up.
  • A welcome menu on WhatsApp and Telegram after the first reply, or whenever the person types "menu".
  • In the Inbox: a team filter, a "My teams" view, team badges and moving a conversation to another team. Alerts go to that team's members.
  • Also in the API and MCP: /v1/teams and the team platform tools.

The dashboard in English, Portuguese and Spanish

The SuperCognit dashboard now speaks European Portuguese and Castilian Spanish as well as English, and the emails it sends you follow your language. Polish and Croatian followed later in the month (see Polish and Croatian).

  • Pick your language on your Profile page or under the sign-in form; every screen switches at once, without a reload.
  • Until you choose, the dashboard follows the language you used on the website, then your browser.
  • Dates and numbers follow your language.
  • Emails to you β€” sign-in links, invitations, new leads, hand-over alerts, low credits and more β€” arrive in your language.

Agents a person answers

A new kind of agent with no AI at all: a chat page and channels where every message goes straight to your team in the Inbox. For teams that want a real person on every reply.

  • Choose "A person answers" when you create an agent, or switch an existing one under General β†’ Who answers. Your AI settings are kept if you switch back.
  • Every message waits for your team, inside and outside business hours. The AI never answers.
  • No AI wording anywhere: no "AI chatbot" in the footer, "Write a message" in the box, and the widget shows whether the team is around.
  • Staff only: under Access β†’ Who can chat, list the email addresses or whole domains allowed to chat. They sign in with a confirmed email; everyone else sees your message.
  • Works on the chat page, the widget, WhatsApp and Telegram.
  • Also in the API and MCP: type "person" on /v1/products and on create_agent and update_agent.

September 2026

One platform MCP connection per workspace

Each workspace now has its own platform MCP URL, so you can keep several workspaces connected in Claude, Cursor or any MCP client at the same time instead of disconnecting and reconnecting.

  • The URL is mcp.supercognit.com/platform/<workspace>/mcp β€” find yours under Integrations β†’ Platform MCP, with ready-made Claude Code and mcp.json snippets named after the workspace.
  • A key from another workspace is refused on that URL, so a connection can never operate the wrong workspace by mistake.
  • The shared /platform/mcp keeps working for a single connection.

Invite links, resend and a clearer Team tab

Every workspace invitation is now a link you can share on WhatsApp or Slack, and the Team tab shows when each invite was sent, lets you resend it, and keeps revoked invites with their date.

  • Copy link on every pending invite: whoever opens it joins the workspace with the role you chose, signed in or after creating an account.
  • Sent and resent dates on each invite, and a Resend button (at most once a minute).
  • Revoked invites stay listed with the date they were withdrawn, with an Invite again button.
  • The invitation email now opens the invitation directly instead of the login page.
  • Also in the API and MCP: /v1/invites (list, create, resend, revoke) and the list_invites, invite_member, resend_invite and revoke_invite platform tools.

Saved replies, team presence and automatic assignment

The last pieces for running live support from SuperCognit: canned answers on a slash, an Available / Away switch, new hand-overs assigned to whoever is online, and an Inbox that updates itself.

  • Saved replies under Settings β†’ Saved replies. Type / in the reply box to pick one; {{name}} becomes the visitor's first name and {{agent}} yours.
  • An Available / Away switch in the Inbox, and a dot next to every teammate who is online.
  • New hand-overs go to the least busy teammate who is online, and only that person is alerted. Turn it off per agent to let the team pick.
  • The Inbox list refreshes itself, so new and waiting conversations appear without a reload.
  • A visitor on the web who asks for a person is asked for an email. If they have left by the time you reply, the answer is also emailed to them with a link back to the chat.
  • With human support on, the widget header shows whether your team is online or the AI is answering on its own.
  • Also in the API and MCP: /v1/saved-replies, presence on /v1/members, and saved-reply platform tools.

Know when a visitor is waiting

When a conversation needs a person, the right people hear about it: by email, with a badge on the Inbox and, if they want, a desktop notification.

  • An email when a visitor asks for a person, when a conversation is assigned to you, and when the visitor writes again while waiting β€” at most one every 10 minutes per conversation.
  • Owners, admins and support agents hear about every hand-over by default; people who build agents only about their own. Everyone sets their own under Inbox β†’ Alerts.
  • A badge on the Inbox counts the conversations waiting for a person and yours where the visitor wrote last.
  • Optional desktop notifications, turned on per browser.
  • Four new webhooks for your own tools: conversation.handoff_requested, conversation.assigned, conversation.team_replied and conversation.resolved.

Hand the conversation to a person

Turn on human support for an agent and it hands the conversation to your team when a visitor asks for a person or when it cannot help. While someone from the team is on it, the agent stays quiet.

  • A new Support tab in the agent editor: turn it on, choose when the agent hands over, and set your business hours.
  • A "Talk to a person" button on the chat page and in the widget β€” always, after the agent's first answer, or never.
  • The agent hands over by itself when the visitor asks for a person or when it is stuck, and tells the visitor the team is on its way.
  • While a person holds the conversation the agent does not answer; messages wait for your team, on the web, WhatsApp and Telegram alike.
  • Outside business hours you choose: the agent keeps helping, or the conversation waits in the queue for the team.
  • If nobody from the team replies within 10 minutes the agent comes back and carries on, so no one is left waiting. Set anything from 2 to 120 minutes.
  • Configurable from your own code as humanSupport on /v1/products and the update_agent platform tool.

Reply to visitors from the inbox

Your team can now answer a conversation from the Inbox. The reply reaches the visitor wherever they are talking β€” the chat page, the widget, WhatsApp or Telegram β€” signed with the team member's first name.

  • A reply box under every conversation, with emoji, Enter to send and a note of which channel the answer goes out on.
  • Visitors see the team member's first name and photo next to the message, marked as someone from your team β€” never their email address.
  • An open chat page or widget shows the reply within seconds, without a reload.
  • On WhatsApp, Meta only allows free-form replies within 24 hours of the customer's last message; after that the reply box tells you instead of failing silently.
  • Whoever replies first becomes the conversation's owner if nobody had it yet.
  • Also in the API and MCP: POST /v1/sessions/{id}/reply and the reply_to_conversation platform tool.

Leads without the interrogation

Agents now offer to take a visitor's details at the right moment β€” after answering, once someone asks about prices, availability or a quote β€” and collect them through a short form with a consent checkbox instead of spelling out an email in the conversation.

  • A per-agent policy: when the visitor shows interest (the default for new agents), early, form first, or off.
  • A contact card on the chat page and in the widget: name, email and the questions you configure, with a consent checkbox. On WhatsApp and Telegram the agent asks in the conversation instead.
  • New agents get a lead tool automatically; leads land under Leads and in your CRM if one is connected, with the page they came from.
  • You get an email for every new lead, and visitors who left their details are no longer limited to three conversations.
  • Sites that already know the visitor can call SupercognitWidget.identify({ email, name }) β€” signed on your server to mark it verified β€” and the agent never asks again.
  • Available from your own code too: leadCapture on the platform MCP tools and on POST/PATCH /v1/products.

WhatsApp without paying for every reply

From 1 October Meta bills every reply an agent sends on WhatsApp once a number has used its free monthly allowance. A new cost control answers up to a budget you set, then moves the person to your web chat with the conversation intact.

  • Off by default. Turn it on per agent under Channels β†’ WhatsApp cost control; if you are happy to pay Meta, nothing changes.
  • Two budgets: answer for a number of hours from the person's first message, and a monthly cap on delivered messages per number β€” 1,000 matches Meta's free allowance.
  • Past the budget the agent sends a short reminder with a private link instead of an answer, a fixed number of times, then goes quiet. A week of silence starts the person fresh.
  • The link opens your web chat with the WhatsApp conversation already there, so either side can carry on. In the web chat it shows as a card.
  • The reminder comes in the agent's language, or write your own with a {{link}} placeholder.
  • Telegram is not affected. Also available as whatsappHandoff on the platform MCP tools and on /v1/products.

Choose the countries your agent serves

A country rule on the Guardrails tab blocks the countries you list, or serves only the ones you list, so an agent built for one market stops spending on visitors it will never serve.

  • Two modes: block the listed countries, or serve only the listed countries. Tor exit nodes can be listed too.
  • On the chat page a blocked visitor sees a short notice in their language and nothing about the agent; the widget simply does not appear.
  • Applies to the chat page, the widget and the chat API. WhatsApp, Telegram, the public API and your own preview are never affected.
  • Visitors whose country cannot be determined are always served β€” this is a cost and noise filter for markets you do not serve, not a security control.
  • Manage it from your own code: get_guardrails and set_guardrails on the platform MCP tools, and GET/PATCH /v1/products/{id}/guardrails.

An inbox your team can work

Conversations now carry a status, an assignee, a priority, tags and internal notes, and the Inbox has views for what needs a person β€” the groundwork for your team taking over from the agent.

  • Statuses: open, needs a person, with a person, resolved. A visitor writing into a resolved conversation reopens it.
  • Inbox views β€” All, Mine, Unassigned, Needs a person, Resolved β€” with counts, a tag filter, and status, assignee and priority on every row.
  • Take a conversation, hand it to a colleague, set its priority, tag it and leave internal notes the visitor never sees; every change is in the conversation's history.
  • Tags are managed under Settings β†’ Tags, with usage counts.
  • A new agent role for support staff: inbox only, no access to agent building, billing or settings. Seats count against your plan.
  • In the API and MCP too: /v1/sessions filters and workflow, notes, conversation tags and members, plus nine new platform MCP tools.
  • Coming next: replying from the inbox, and the agent staying quiet while a person handles the conversation.

Analytics: who visits, who talks, who converts

A new Analytics section in the dashboard shows how people find and use your agents β€” visits, conversations, messages and leads over time, the busiest hours, and a map of where they come from. Pro plans get a live map of who is on the site right now.

  • Overview, Conversations, Visitors and Leads pages with a 24h / 7d / 30d / 90d range, an agent filter and your own timezone.
  • A world map of visits, conversations or leads by country and city, from coarse network location β€” never a precise position, never an IP.
  • Busiest hours as a weekday Γ— hour grid, so you know when to staff and when to let the agent handle it.
  • Pro and Enterprise: the live map of visitors online and chatting now, mean response times, the lead funnel through to CRM delivery, devices, browsers, languages, previous-period comparison and CSV export.
  • Tools and MCP servers too: calls per tool with outcomes, durations and cost share, and how each MCP server you publish is used by external clients.
  • Everything is also in the API (/v1/analytics/…) and in the platform MCP tools, so your own dashboards and assistants can ask the same questions.

Options as cards, not paragraphs

When the agent has a handful of things to show β€” rooms, products, plans, appointments β€” it now lays them out as cards with an image, a title and a button, and the visitor's tap flows straight back into the conversation.

  • Two to ten options as a card strip or grid: image, title, subtitle, a price or badge, and a button that posts the choice back into the chat.
  • A "More details" sheet on every card, with a gallery, address, phone, email, hours and link, plus longer sections.
  • Works on the chat page and in the widget. On WhatsApp cards go out as an interactive carousel, on Telegram as photo cards with buttons β€” a tap becomes the same choice.
  • Card images only ever come from data a tool returned in that turn, so the agent can't make one up.

The agent plays your videos

Add YouTube or Vimeo videos to an agent's Media tab and it plays the right one inline when a visitor asks for a tour, an intro or a demo β€” in our own player, not the native embed.

  • Up to 25 videos per agent, added from the new Media tab in the editor.
  • Plays inline on the chat page and in the widget: a click-to-play poster, our controls and your agent's accent colour.
  • On WhatsApp and Telegram the agent sends the video's title and link instead.
  • Manage media from your own code too, through the platform MCP tools and /v1/agents/{id}/media.

Website import works behind bot challenges

Some sites greet crawlers with a challenge page instead of content. Import now reads those through our own Chromium, so building an agent from a protected site no longer fails at the first step.

  • Sites behind bot challenges are fetched with a real browser and imported like any other.
  • Nothing to configure β€” the importer picks the route on its own.
  • Same agent, same knowledge base, same cited answers as a plain import.

Better answers from big knowledge bases, fresher on a schedule

Retrieval now adapts to the size of your knowledge, keyword search matches exact names again, and scheduled re-syncs only redo the pages that actually changed.

  • Retrieval sizes itself to the corpus instead of always pulling a fixed five passages, so large knowledge bases stop dropping the right page.
  • The keyword arm of hybrid search was repaired: exact product names, SKUs and codes match again.
  • Scheduled refresh skips pages whose content hasn't changed, so a re-sync is cheaper and faster.
  • Refresh cadence is set per source β€” daily on Starter, every 6 hours on Pro, hourly on Enterprise.

Plans now include usage credits

Every paid plan comes with a monthly allowance of usage credits, so the subscription covers real conversations from day one instead of billing every reply separately.

  • Starter and Pro each include a monthly allowance of usage credits (amounts on the pricing page); the 7-day trial carries a quarter of it.
  • Plan credits reset at renewal; credits you buy as a top-up never expire.
  • Switching between Starter and Pro changes your existing subscription in place, prorated, and keeps a running trial.

August 2026

A portal for partners

Partners now have one place for everything client-facing: the workspaces you manage, your firm's details and brand, the sales deck and your certifications.

  • Clients, Details, Brand, Presentations and Certifications β€” the whole partner relationship in one portal.
  • Put your logo and colours on the sales deck and export it to PDF to send ahead of a meeting.
  • Work inside every client workspace from the dashboard login you already have β€” no separate accounts.

Turn conversations into leads β€” with or without a CRM

Your agent can ask for the details that matter and file the answer where you already work: straight into Pipedrive or HubSpot, or into SuperCognit itself if you don't run a CRM.

  • Connect Pipedrive or HubSpot and a captured lead lands as a real deal, in the right pipeline and stage.
  • No CRM? We keep the leads for you β€” visible in the inbox, listed on their own page, and pushed onward by webhook or API.
  • Change what a capture asks for whenever you like, without rebuilding the tool or detaching it from your agents.
  • If your CRM is unreachable, leads wait in line and go through the moment it answers again.

The API reference is public

Everything the dashboard does, your code can do too β€” and the full reference now lives online, interactive and open to everyone, next to a new page explaining what the API covers.

  • Browse every endpoint at api.supercognit.com/docs and try calls straight from the page.
  • Create, publish and update agents and MCP servers, tools and knowledge from your own code.
  • Receive conversations as they happen through signed webhooks, or read the transcripts later.

Connect SuperCognit to Claude, Cursor and other AI clients

Your workspace now speaks MCP in both directions: as well as publishing your own MCP servers, you can plug SuperCognit itself into the AI client you already work in.

  • Create and edit agents, knowledge bases and tools straight from your assistant.
  • Read your inbox and your contacts without leaving the client you work in.
  • Works with any MCP-capable client, Claude and Cursor included.

Agents that use a real browser

The new browser tool lets an agent open a site, fill in a form and bring the answer back into the conversation β€” for the jobs that live behind a portal instead of an API.

  • Check availability, submit forms and collect documents from sites with no API.
  • Longer jobs run in the background, and the agent tells the customer the moment they finish.
  • Results come back as text or as a PDF, ready to use in the chat.

WhatsApp and Telegram channels

Your agent now answers where your customers already are. Connect a WhatsApp Business number or a Telegram bot and the same agent picks up the conversation.

  • One agent, every channel β€” same prompt, same knowledge, same tools.
  • Conversations from every channel land in the shared inbox.
  • Customers get an answer in their own language, whichever channel they wrote from.

withnodes is now SuperCognit

New name, new site, same platform. The rebrand landed across the product, together with a redesigned homepage and a site that finally speaks more than one language.

  • Everything you built keeps working β€” agents, domains and integrations are untouched.
  • The site now ships in English, Portuguese and Spanish.

July 2026

From your website to a working agent in two minutes

Paste your address and we read your public pages, draft the prompt and build the first knowledge base for you. You review it, adjust the tone and publish.

  • The import wizard takes you from a URL to a live draft agent.
  • Your pages become knowledge sources you can edit, extend or remove.
  • Also available through the API, for agencies onboarding clients in bulk.

Public or sign-in-only agents

Every agent now has an access mode, so a pre-sales assistant and a customers-only one can live side by side in the same workspace.

  • Open: anyone with the link can start chatting.
  • Sign-in required: visitors log in before the first message.
  • Widgets embedded on your own site keep working either way.

Inbox and contacts

Every conversation your agents have, in one place β€” with a contact record behind each one, so you can see what a customer asked before they wrote again.

  • Read full transcripts from every channel in a single inbox.
  • Contacts gather the conversations of each person who wrote to you.
  • Knowledge and tools moved into a cleaner home in the dashboard at the same time.

Simpler plans, priced in euros

Two plans β€” Starter and Pro β€” each with a seven-day free trial, and a much clearer picture of what a published agent costs to run.

  • Choose a plan and start the trial straight from the pricing page.
  • Publishing an agent now tells you upfront what running it will cost.

Embeddable widget, webhooks and a bigger API

Three ways to take your agent off our pages and put it inside your own product.

  • Drop one script tag on your site for a chat bubble that opens instantly.
  • Webhooks push conversation events into your own systems.
  • The public API covers agents, knowledge and conversations.

Agents that answer in your customer's language

Publish once and your agent replies in fourteen languages out of the box, following whoever wrote in.

  • Names, descriptions and greetings can be translated language by language.
  • The customer never has to pick a language β€” the agent simply follows theirs.

Faster answers, web search and deeper thinking

A round of model-side work made agents quicker on repeat questions and noticeably better on hard ones.

  • Repeated context is reused between messages, so replies start sooner and cost less to run.
  • Agents can search the web when your own knowledge doesn't cover the question.
  • Harder questions get more thinking time, and long conversations keep their thread.

Launch on your own domain

Your agent can live at your address instead of ours. Connect a domain and the certificate and routing are handled for you.

  • Point a subdomain such as chat.yourbrand.com at your agent.
  • Set it up in the dashboard; it goes live as soon as the DNS records match.

Bring your own knowledge

Agents can be grounded in your documents, not just in your prompt β€” and they show where an answer came from.

  • Upload PDFs, Word documents, text and markdown files.
  • Add website pages and Google Docs links that re-sync on a schedule.
  • Answers cite the source they were built from.

Charge for your agents

Turn a published agent into a product: set a price, and subscriptions, invoices and payouts are handled for you.

  • Per-seat subscriptions for the teams that buy your agent.
  • Checkout, invoicing and refunds run on the platform.
  • A clear breakdown of what you earn on every subscription.

Partner program

Agencies and consultancies can build on SuperCognit for their own clients, at wholesale pricing.

  • A partner portal for the client workspaces you run.
  • Wholesale rates on agent seats and MCP servers.

Agents that do things, not just answer

Agents run a multi-step tool loop: they call your APIs, search your knowledge and use your MCP servers to finish a job inside a single conversation.

  • Connect any HTTP API as a tool, no code required.
  • Publish your workspace's tools as an MCP server other clients can connect to.
  • Shared tool and knowledge libraries, so several agents reuse the same setup.

Human ambition. SuperCognit intelligence.

Build with the latest

Everything on this page is live today β€” free for 7 days.