Confluence, read-only.

The documentation usually exists. It just lives in a wiki last updated two reorgs ago. Firstweek reads the spaces you connect, read-only, along with the Slack threads explaining why half of it is wrong, and writes one document for one new hire.

What Firstweek reads from Confluence

Architecture decisions, runbooks and space-level docs
Project tickets and documentation content, where Confluence and Jira share a workspace
Page structure and metadata needed to attribute a claim to its source page

What shows up in the onboarding artifact

Confluence content shows up as the "how we work" and "why things are the way they are" parts of the artifact: decisions and norms that are technically written down, just not where a new hire would look on day one.

Read-only, and the raw content is never stored

Every connection, Confluence included, is read-only: Firstweek never writes to, changes or deletes anything in your tools. Confluence content is processed in memory and never stored. Only AI-generated summaries persist. A citation can quote up to 200 characters of a summary, and an admin can turn that off.

Full detail: the security page covers data handling end to end, and the subprocessors list shows exactly which Confluence data is processed.

Other read-only connections: Slack · HubSpot · Salesforce · Google Drive · Microsoft 365 · GitHub · Jira

Run Firstweek on your next real hire. 30 days. Then we talk about whether it's worth keeping.

See a sample artifact →