Skip to main content
Connic

Knowledge Ingest

Connect the places where your team already writes: Notion, Confluence, Coda, or any website. Connic syncs their content into your agents' knowledge base on a schedule, so answers stay current without manual uploads.

Knowledge Base DocsQuickstart

Featured

Notion

By Connic

Connect a Notion workspace and keep pages and databases synced into your knowledge base. Agents retrieve the current version, not a stale export.

Workspace appAuto-sync
View details

Website Crawler

By Connic

Point the crawler at your docs, help center, or blog. Pages are converted to clean markdown and re-crawled on your schedule.

WebsiteAuto-sync
View details

All knowledge ingest

Notion

By Connic

Connect a Notion workspace and keep pages and databases synced into your knowledge base. Agents retrieve the current version, not a stale export.

Workspace appAuto-sync
View details

Confluence

By Connic

Sync Confluence spaces on a schedule you choose. Pages are chunked and embedded so agents can answer from the wiki instead of guessing.

WikiAuto-sync
View details

Coda

By Connic

Sync Coda docs, pages, and table rows into the knowledge base, so agents answer from the doc your team actually edits.

DocsAuto-sync
View details

Website Crawler

By Connic

Point the crawler at your docs, help center, or blog. Pages are converted to clean markdown and re-crawled on your schedule.

WebsiteAuto-sync
View details

How knowledge ingest works

One pipeline for every source: connect, scope, sync, retrieve.

01

Connect a source

Authorize Notion, Confluence, or 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.

02

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.

03

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.

04

Agents retrieve it

Every agent in the project can query the knowledge base at run time and answer from the freshest synced version, with namespaces to keep sources separated.

Knowledge ingest FAQ

Knowledge ingest is a set of sources that sync external content into your project's knowledge base automatically. Instead of uploading documents by hand, you connect Notion, Confluence, Coda, or a website once, and Connic keeps the content chunked, embedded, and retrievable on a schedule you choose.

Uploads are one-time snapshots; a synced source stays current. When someone edits the wiki page or publishes a new doc, the next sync updates the knowledge base without anyone re-uploading anything. Both end up in the same knowledge base and are retrieved the same way.

Notion, Confluence, and Coda for internal content, plus a website crawler for anything public like docs or help centers. More sources are on the way.

Each page is converted to clean text, split into chunks, and embedded for semantic search in your project's knowledge base, filed under a namespace per source. Agents query it at run time and retrieve the most relevant chunks, no matter which source they came from.

No. Knowledge ingest is read-only by design: sources are pulled into the knowledge base, never written to. When an agent should act on an external system, that is what connectors are for.