Documentation sets I run at Atlassian, and one of your own Help Center articles rebuilt to serve a clinician and Fin at the same time.
All three are live and public. Worth opening rather than taking on trust.
Several hundred articles spanning administration, agent workflows, ITSM, incident and change management, knowledge base, and integrations. I have maintained and extended it single-handedly for the past six months, and worked on it for six years.
support.atlassian.com/jira-service-management-cloud/resources →The entire Assets documentation set, started from a blank page and owned since. Structure, standards, and maintenance, all of it mine.
support.atlassian.com/assets/resources →A visual, step-by-step guide that explains a CMDB in plain language, written with Sales and published in twelve languages.
atlassian.com/…/assets-cloud-get-started →One reader is a clinician skimming for an answer. The other is Fin, retrieving one on their behalf. The same article can serve both.
Heidi uses role-based access control to manage what each team member can see and do. Roles are divided into Administrator, Clinician, Assistant, and Template Manager, each tailored to specific team functions.
The Administrator role is for users who need full access to manage the workspace. The Clinician role is designed for providers who need clinical tools and documentation. The Assistant role is for support staff who help without owning core sessions…
Continuous prose, with permissions embedded mid-sentence. No single role can be retrieved without the others.
Heidi has four roles. Each controls what a team member can see and do.
Each role becomes one retrievable unit, with permissions stated explicitly rather than implied.
A support AI retrieves passages, not pages. When four roles sit inside continuous paragraphs, a question like "can an assistant change team settings?" returns a passage mentioning all four, and the model has to infer which sentence applies. Most wrong answers begin here, in the structure of the source rather than the model reading it.
Separating each role into its own unit, with permissions stated as can and cannot, gives the retrieval step a single clean passage to work from. The facts are unchanged from your current article; only the structure differs. I measured this at Atlassian against a six-point quality check: 93 percent for the retrieval-ready version, 63 for the one written for a human alone.
Your posting describes this as much as building the system as writing inside it. This is the system I would put in place.
Twelve years in content altogether. I started as a copywriter in advertising, working on global brands for five years before moving into tech, then became Airtasker's first writer, which meant establishing a content function rather than joining one. I also spent a period as a patient some years ago, long enough to notice the difference between a clinician who is present and one buried in administration. It is a large part of why this particular role interests me.