Skip to main content
Connic

Coda

By Connic

Keep Coda docs and tables in sync with your agents

DocsAuto-sync

How the Coda source works

Coda docs mix prose with structured tables, which makes them a natural knowledge source for agents: the runbook and the escalation matrix live in the same place. The Coda source syncs both into your Connic knowledge base.

You connect with a Coda API token and pick the docs to sync. Pages are converted to text, and table rows become individual entries with their column values preserved, so an agent can retrieve one row as precisely as one paragraph. Everything refreshes on the schedule you choose.

What gets synced

Pages

Doc pages and subpages, converted to clean text before chunking.

Tables

Each row becomes its own knowledge entry with column values preserved.

Doc structure

Page hierarchy is kept in entry metadata so retrieval can be scoped later.

Configuration, in depth

Everything you control when connecting Coda to a project.

Connection

API token*
Coda API token. The sync only reads docs this token can access.

Content scope

Docs
Coda doc links or IDs, one per line. Leave empty to sync every doc the token can read.
Include hidden pages
Also sync pages that are hidden in the doc's navigation.
Include tables
Sync table rows as individual knowledge entries.

Sync behavior

Where synced content lands and how often it refreshes.

Target namespace
Knowledge base namespace the synced entries are filed under. Use dots to nest, e.g. sources.notion.
Sync interval
How often the source is checked for changes. Each run only reprocesses content that changed.
When content is deleted at the source
Pages or rows deleted in Coda can be removed from the knowledge base on the next sync, or kept as they were last synced.

Information

Publisher
By Connic
Type
Docs
Sync schedule
Every 15 minutes to weekly
Documentation
Knowledge Base Docs

Coda knowledge source FAQ

It syncs the pages and tables of the docs you select. Pages are converted to text, and each table row becomes its own knowledge entry with column values preserved.

Yes. Rows are stored as separate entries, so a semantic query like an escalation contact or a pricing rule can surface exactly the matching row.

List specific doc links or IDs in the configuration. If you leave the list empty, every doc the API token can read is kept in sync.

As fresh as your sync interval, from every 15 minutes up to weekly. Each run only reprocesses pages and rows that changed since the last sync.
Need Coda content behind a production agent?

Tell us where your knowledge lives, how fresh it needs to be, and who is allowed to see it. We will map that to knowledge ingest scopes, namespaces, and the retrieval setup your agents need.

Talk to Sales