
Turn 👍/👎 into fixes with the AI feedback report
Votes only help if someone reads them. The new Feedback page puts every 👍/👎 in one place, and the AI report reads the last 30 days for you: what went wrong, how many people it hit and what to change.
From October 1, WhatsApp charges for every business reply. Read the migration playbook
Resources
Launch news, customer stories, honest comparisons and industry playbooks — from the team building the platform.
Blog

Votes only help if someone reads them. The new Feedback page puts every 👍/👎 in one place, and the AI report reads the last 30 days for you: what went wrong, how many people it hit and what to change.

An agent that knows your prices, follows your quote procedure and checks live stock uses four different things to do it. Here is which is which, and why skills now have a page of their own.

A full month of releases: two new languages, version history you can restore from, 👍/👎 feedback that reaches you, a progress line instead of a bare "Thinking…", teams for hand-overs, agents answered only by people, and an Inbox that shows the whole answer.

An agent that checks your documents, your systems and the web before it answers takes a few seconds per step. Here is where the time goes, what visitors now see while it works, and what you can change to make it faster.

Polish and Croatian are now full SuperCognit languages: agents reply in them, and the chat page, the widget, WhatsApp and Telegram, the dashboard, the emails and the website are translated end to end. That makes 14 agent languages.

Every change to an agent, an MCP server or a tool now leaves a version. See who changed what and from where, compare any version with the live one, restore it in one click, and undo the restore if you change your mind.

The thumbs under every reply now reach your dashboard. Here is how to set what each vote asks, where to read the results, and how to turn a 👎 into a better agent.

In Portugal, Spain and Latin America a customer question often arrives as a 40-second voice note or a photo of a broken part. Here is how a SuperCognit agent handles them, and how your team can answer the same way from the Inbox.

An agent that only answers questions does not need to know who it is talking to. An agent that shows an invoice, changes a booking or sends a private link does. Here is how to prove a visitor's phone, email or customer number with a code, and when you can skip the code.

One shared queue works for a team of three. Once sales, support and billing are different people with different hours, hand-overs need to land in the right place. Teams do that: the AI picks the queue, each team keeps its own hours and limits, and customers are told their place in line.

We build AI agents, and we also think some conversations should never reach one. Person agents are a chat page, a widget and channels where every message goes to your team. No AI replies, no AI wording, one Inbox.

SuperCognit agents can now hand a conversation to a person. Your team replies from the Inbox on the web, WhatsApp and Telegram, the agent stays quiet while they do, and it comes back if nobody answers.

Ten days after the last update: a WhatsApp cost control to have ready before Meta's 1 October pricing change, a contact card that captures leads without spelling out an email in the chat, a country rule for markets you do not serve, and the first step towards people taking over from the agent.

Security researchers disclosed an active campaign — tracked as Deadbugz — distributing a malicious MCP server through GitHub pull requests. It answers normally for two tool calls, then rewrites its own tool metadata on the third to hunt for credentials. Nothing was compromised, but the technique is the story.

September's release: agents show options as cards and play your videos inline, paid plans now include monthly usage credits, and a batch of smaller things — protected-site import, better retrieval on large knowledge bases, a partner portal.

On September 2, CISA added a LiteLLM authentication bypass to its Known Exploited Vulnerabilities catalog — the first Model Context Protocol flaw on that list. A critical bug in AWS Labs' own Postgres MCP server followed a week later.

Selling MCP means selling correct, cited answers and permitted actions inside the AI tools people already use — not the protocol. Here is how to pitch the benefits, package it by industry and department, sell it inside a company, and run MCP servers for many customers from one place.

You can automate WhatsApp Business in an afternoon: connect your number to an AI agent built from your own website, and it answers, qualifies and hands off around the clock. Here is the setup step by step, what to automate first, what to keep human, and what it costs once Meta bills every reply from 1 October 2026.

A hotel AI reservation agent answers the questions guests ask before they book, checks availability through your booking engine, and either completes the handoff or captures the enquiry — around the clock, in the guest's language. Here is how it works, what it connects to, and how group and event bookings fit in.

Wonderchat is a fast website chatbot; Intercom Fin is a support agent inside Intercom. Neither was built to qualify leads and write them into a CRM. Here is how each handles lead qualification, a side-by-side table, and a third option to test against both.

A chatbot webhook is an HTTPS endpoint your chatbot platform POSTs JSON to when something happens — a new conversation, a finished reply, a captured lead. Here are the events, the payloads, how to receive them in n8n, Make and Zapier, how to verify the signature, and the mistakes that lose data.

On 28 August Anthropic opened a research preview letting AI agents operate lab and manufacturing hardware through MCP-compatible interfaces. It has nothing to do with a support chatbot — and it is still worth twenty minutes, because it tests whether the protocol we built on actually generalizes.

A professional company MCP server needs six things before you share it: current-spec auth, a clear data boundary, cited answers, fresh content, accountable tools and a domain that says who it speaks for. The full MCP checklist, with checks you can run.

To sell access to your MCP server you need to solve three things: who may connect, what a seat costs, and how the money reaches you. Here is how per-seat pricing and built-in Stripe subscriptions and payouts work in practice.

Sales training fails in the gap between the workshop and the next real call. An AI roleplay agent built from your own playbook gives reps unlimited practice reps — here's how to set one up in an afternoon.

A lead capture chatbot answers the visitor's questions, asks the qualifying ones, takes consent, and writes a real contact and deal into HubSpot or Pipedrive with the transcript attached — or books the meeting. Here is how it works on the website and on WhatsApp, how to write the qualifying questions, and what to measure.

Article 50 of the EU AI Act has applied since 2 August 2026: if people can talk to your AI, you have to tell them — at the point of interaction, in their language, on every channel. Here is what the rule asks of a customer-service chatbot, what it does not, and a checklist you can finish in an afternoon.

From 1 August 2026 Meta bills Business Agent conversations on tokens consumed, and from 1 October it starts charging for service replies again. Two different meters, five weeks apart, and most of the coverage only mentions one.

The specification makes OAuth 2.1 mandatory. Surveys of the public server ecosystem suggest only a small minority implement it. If you are about to connect an MCP server to an assistant that can see your work, that is the first thing to check.

Connecting a remote MCP server takes a URL and about ten seconds. That is the feature. It is also why a new category of shadow IT now has a name and a threat model.

The 2026-07-28 revision removed the initialize handshake and the session header. It makes MCP servers scale like any other HTTP service — and it leaves every client that has not caught up behind.

Anthropic donated the Model Context Protocol to the Agentic AI Foundation under the Linux Foundation in December 2025. If lock-in was your objection to building on MCP, it no longer holds.

Four protocols, four layers of the same problem: letting software spend money on your behalf without it becoming a disaster. Here is what each is actually for, and what is still genuinely unsettled.

Everything you do in the dashboard, you can also do over HTTP: create agents and MCP servers, attach tools and knowledge, publish them, read every transcript and receive webhooks. Here is the whole surface — and the first call you will make.

Packaging your expertise as a paid MCP server means turning the material you already deliver into a knowledge base clients query from inside Claude — with per-seat billing built in, and no code to write.

The pattern that works for agencies offering MCP servers to clients: one server per client, built from their website and documents, published on their own domain — no code, isolated workspaces, billable per seat.

Ten examples of company MCP servers — private internal brains, public knowledge servers and paid per-seat products — with the questions each one answers.

From October 1, 2026, WhatsApp charges businesses for every service message — the replies inside the 24-hour customer window that used to be free. Here's what changes, what it costs you, and a practical playbook to move conversation volume to channels you own.

With WhatsApp charging for every business reply from October 2026, teams are rethinking where customer conversations should live. Here are the real alternatives — web concierges, Telegram, and an omnichannel AI agent — compared honestly.

Today we're opening SuperCognit to everyone: one platform to build customer-facing and internal AI agents, publish them on your own domain, and get paid — with knowledge, tools, MCP servers and billing built in.

Agencies, consultants and AI builders: package your expertise into agents and MCP servers your clients subscribe to. Wholesale pricing, a partner portal, and a managed cloud underneath — you keep the client relationship.

Building an MCP server: an honest comparison of custom development versus a no-code platform, with a side-by-side table and the three cases where writing your own still wins.

How to secure a company MCP server in three layers: OAuth 2.1 with iss validation and CIMD registration, hard per-workspace isolation, and explicit private, public or per-seat scoping.

How to keep a company MCP current without re-training anything: point the knowledge base at your live website and let scheduled re-syncs — as often as hourly — do the maintenance.

You can put your MCP server on your own domain — a subdomain like mcp.yourcompany.com instead of a platform URL. Here is how custom domains work on SuperCognit, and why the URL you hand out is a brand decision.

To give your MCP server real tools, you describe HTTP endpoints you already have — URL, parameters, auth — and SuperCognit publishes them as callable MCP tools in Claude or any MCP client. No SDK, no server code.

MCP is an open standard, so one MCP server makes your company knowledge available in Claude, Cursor and every other MCP client your team uses. Build it once, without code, and stop maintaining a copy per tool.

An internal MCP server turns your SOPs, policies and onboarding material into a private company brain every AI assistant on your team can query — cited answers, per-seat access, no code. Here is how to build one and keep it current.

How to build a company MCP server your whole team can use inside Claude: one private, cited knowledge base with OAuth 2.1 sign-in, connected once per teammate and kept current from then on.

Turn your company documents into an MCP server in about ten minutes: upload files into a cited knowledge base, choose private or public, publish, and connect it in Claude. No code involved.

Withnodes — the platform at withnodes.com where builders created AI agents and MCP servers — is now SuperCognit. Same team, same technology, a bigger mission: everything you built keeps working, and everything you can build just got larger. Here's what changed, what didn't, and what you can create today.

Everything an MCP server for your company would serve is already on your website. Publishing it as an MCP server is a two-minute import, not an engineering project — here is what changes when you do.

Build your first MCP server for your company without writing code: import your website into a cited knowledge base in about two minutes, upload documents, attach tools, publish. Here is the whole process.

MCP server vs. chatbot comes down to where your audience is standing: a chatbot meets visitors on your website; an MCP server meets your team and customers inside Claude. How to pick — and why one build can give you both.

An API is built for developers; an MCP server is built for AI assistants. A practical comparison of MCP server vs. API — what each one does, where they overlap, and when your company needs each.

MCP — the Model Context Protocol — is the open standard that lets AI assistants read your company's knowledge instead of guessing. A non-developer's guide to what it is and why your knowledge belongs on an MCP server.

An MCP server gives AI assistants like Claude direct, permissioned access to your company's knowledge and tools. Here's what that means in plain English — and how a business gets one without writing code.

Illusion.ws — the AI illusion generator behind aesthetic illusion art, hidden-pattern images and optical illusion experiments — has been acquired by SuperCognit. Here's what that means, a practical guide to creating AI illusions today, and what illusion creators can build (and sell) on SuperCognit now.