Team context and connectors | kanman documentation

Teams know a lot that is not on the board: runbooks, architecture decisions, the README of a service, a Confluence space, a Notion page. Team context lets kanman answer questions from that knowledge in Slack and Microsoft Teams. Every answer names its sources.

Turn on team context

Team context is off for every team by default.

Open the team, then Settings, Team context (/<workspace>/teams/<team>/settings/context).
Turn on Let kanman answer from team context.
Add sources under Add a source (see below).

Owners and admins can change the team context; everyone in the team can see which sources it has.

Source types

Type	What kanman reads	Notes
Upload	PDF, Markdown, Word, or an image with text, up to 25 MB	Reading text in images needs the team’s own Anthropic key or kanman’s model access.
Web page	A public page at an https address	Choose under Keep up to date whether kanman reads it again Daily, Weekly or Never.
Repository docs	READMEs, architecture decision records and the docs folder of a GitHub or GitLab repository	Pick the parts under What to include. kanman needs access to the repository through the team or your own code host connection.
GitHub issues and more	Issues, pull requests, the wiki and discussions of a GitHub repository	Pick the parts under What to include.
GitLab issues and more	Issues, merge requests and the wiki of a GitLab project	Pick the parts under What to include.
Confluence	A space, or one page of it	Needs a Confluence connection. Enter the Space key and, optionally, a Page ID.
Notion	A page and its sub pages	Needs a Notion connection. Enter the Page ID.

Give each source a Name, for example “Deployment runbook”, so answers can cite it clearly.

Who may get answers from a source

For each source, choose Who may get answers from it:

Everyone in the team: everyone in the team who asks kanman may get answers from it.
Only people with access in the source: kanman checks, for the person who asks, whether they may see the content in the source itself. For Confluence it checks the page permissions of that person. For repositories it checks the person’s access through their own GitHub or GitLab connection. If the person has no access, kanman does not use that content in its answer.

Only Confluence and repository sources can be checked this way. For uploads, web pages and Notion pages there is nothing to check against, so kanman does not use them with Only people with access in the source; choose Everyone in the team for those.

Manage sources

Each source under Sources shows its type, who added it, who may get answers from it, when it was last updated and its status:

Status	Meaning
Waiting	kanman has not started reading the source yet.
Reading	kanman is reading the source.
Ready	The source is used for answers.
Failed	kanman could not read the source. The reason is shown, for example that a connection no longer works.
Waiting for your runner	Your workspace runs everything on its own runners and no runner has picked up the source yet.

Click Update now to read a source again right away, or Remove to take it out of the team context. A removed source is no longer used for answers.

Connections for Confluence and Notion

Confluence and Notion sources read through a connection, which you add once under Connections on the same page.

Confluence: enter the Confluence address (the https address of your site), the Account email and an API token of that account, or click Sign in with Atlassian.
Notion: create an internal integration in Notion, enter its Integration token, and share the pages kanman should read with that integration in Notion.

Click Check and save. kanman checks the connection before it saves it and tells you if the service rejected the credentials or could not be reached. Tokens are stored encrypted and are never shown again. A connection that stops working is marked Needs attention.

How answers use team context

Every answer names its sources, with a link where the source has one.
When nothing in the team context or on the board fits a question, kanman says so if it was asked directly. When it would speak up unprompted, it stays quiet instead.
kanman only uses content the asking person may see, as set for each source.

Privacy

Content is read with the team’s own model key, or with kanman’s model access if the team has none. See What model providers see.
kanman finds the passages that fit a question by their words. If the team has its own OpenAI key, kanman also searches by meaning, with that key only. kanman never sends your content to a hidden third party for this.
If your workspace runs everything on its own runners, reading sources and answering questions happen on your runners. When no runner is online, kanman says so instead of answering. See Run the self-hosted runner.