Superhuman Docs (Coda)
Keep Superhuman Docs and tables in sync for agents
- Publisher
- By connic
- Syncs
- Pages, Tables, Doc structure
- Set up in
- Retrieval → Sources
- Documentation
- Retrieval Docs
How the Superhuman Docs (Coda) source works
Superhuman Docs, formerly Coda, keeps prose and structured tables together. The source syncs both the runbook and the escalation matrix into connic retrieval.
Connect with a Superhuman Docs 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 configured schedule.
What gets synced
- Pages
- Doc pages and subpages, converted to clean text before chunking.
- Tables
- Each row becomes its own retrieval entry with column values preserved.
- Doc structure
- Page hierarchy is kept in entry metadata so retrieval can be scoped later.
Set up the Superhuman Docs (Coda) source
Add the source under Retrieval → Sources in the environment your agents run in. Each environment keeps its own sources.
Open docs.superhuman.com/account and generate an API token under API settings.
Copy the token and paste it into the API token field below.
The token can only read docs accessible to the associated Superhuman Docs account. Optionally restrict it to read-only access for the docs to sync.
Paste the links of the docs to sync (e.g. https://docs.superhuman.com/d/Team-Handbook_d...), one per line.
Leave the doc list empty to sync every doc the token can read.
Configuration, in depth
Every available control for connecting Superhuman Docs (Coda) to a project.
Connection
- API token*
- Superhuman Docs API token. The sync only reads docs this token can access.
Content scope
- Docs
- Superhuman Docs links or IDs, one per line. Existing coda.io links also work. 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 retrieval entries.
Sync behavior
Where synced content lands and how often it refreshes.
- Target namespace
- Retrieval 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 Superhuman Docs can be removed from the retrieval on the next sync, or kept as they were last synced.
Search it from an agent
Agents search synced content with the retrieval_query tool. A small tool that pins the namespace keeps an agent to this source.
from connic.tools import retrieval_query
async def search_coda(question: str) -> dict:
return await retrieval_query(
question, namespace="sources.coda"
)version: "1.0"
name: support-agent
type: llm
model: connic/gemini-3.7-flash
system_prompt: |
Answer only from what search_coda returns.
tools:
- knowledge.search_codaSuperhuman Docs (Coda) retrieval source FAQ
More retrieval sources
Confluence
By connicSync Confluence spaces on a configured schedule. Pages are chunked and embedded so agents can answer from the wiki instead of guessing.
Auto-syncNotion
By connicConnect a Notion workspace and keep pages and databases synced in retrieval. Agents retrieve the current version, not a stale export.
Auto-syncWebsite Crawler
By connicPoint the crawler at documentation, a help center, or a blog. Pages are converted to clean markdown and re-crawled on the configured schedule.
Auto-sync