Improved
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.
What shipped
- 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.
More updates
The API reference is public
Everything the dashboard does, your code can do too — and the full reference now lives online, interactive and open to everyone, next to a new page explaining what the API covers.
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.
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 — for the jobs that live behind a portal instead of an API.