Retrieval Sources
Connect the places where your team already writes: Notion, Confluence, Superhuman Docs (Coda), or any website. Connic syncs their content into your agents' retrieval on a schedule, so answers stay current without manual uploads.
Featured
Notion
By ConnicConnect a Notion workspace and keep pages and databases synced into your retrieval. Agents retrieve the current version, not a stale export.
Website Crawler
By ConnicPoint the crawler at your docs, help center, or blog. Pages are converted to clean markdown and re-crawled on your schedule.
All retrieval sources
Notion
By ConnicConnect a Notion workspace and keep pages and databases synced into your retrieval. Agents retrieve the current version, not a stale export.
Confluence
By ConnicSync Confluence spaces on a schedule you choose. Pages are chunked and embedded so agents can answer from the wiki instead of guessing.
Superhuman Docs (Coda)
By ConnicSync Superhuman Docs pages and table rows into the retrieval, so agents answer from the doc your team actually edits.
Website Crawler
By ConnicPoint the crawler at your docs, help center, or blog. Pages are converted to clean markdown and re-crawled on your schedule.
How retrieval sources work
One pipeline for every source: connect, scope, sync, retrieve.
Connect a source
Authorize Notion, Confluence, or Superhuman Docs (Coda) with a scoped token, or point the website crawler at a URL. Connected sources read only what you share with them; the crawler stays inside the boundaries you set.
Scope what syncs
Pick spaces, pages, databases, labels, or crawl boundaries. Content outside the scope is never read, and every source syncs into a namespace you choose.
Sync on a schedule
From every 15 minutes for API-backed sources, or every 12 hours for website crawls, up to weekly, Connic pulls changed content, converts it to clean text, chunks it, and embeds it for semantic search. Unchanged pages are skipped.
Agents retrieve it
Every agent in the project can query the retrieval at run time and answer from the freshest synced version, with namespaces to keep sources separated.