Skip to content

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

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.

What shipped

  • 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 — daily on Starter, every 6 hours on Pro, hourly on Enterprise.

← All updates

More updates

A Feedback page, with an AI report

Every 👍/👎 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 👎 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 👎 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 👎: 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.

Human ambition. SuperCognit intelligence.

Build with the latest

Everything on this page is live today — free for 7 days.