AI-assisted curation: optional, draft-only, and human-governed
An optional feature helps administrators turn selected undefined-term findings into reviewable glossary drafts. It shipped in v5.0 (August 2026) and is part of production v6. It never approves, publishes, or overwrites a glossary term automatically.
Last updated: 13 October 2026
What the feature does
- An eligible administrator runs the existing Confluence terminology scan.
- The administrator selects a bounded set of undefined-term findings (up to 10 per request) and chooses Generate draft candidates.
- The feature groups the selected terms and proposes a canonical term, aliases, a plain-language draft definition, and source-page references.
- The administrator reviews, edits, selects, or discards each candidate.
- Selected candidates become ordinary glossary drafts.
- The existing four-eyes workflow remains required before a term can become approved.
The benefit is reduced manual drafting effort after a scan. It is not a legal interpretation service, a compliance decision-maker, or a guarantee of a correct definition.
What it does not do
- It does not run automatically or scan an entire Confluence site for AI processing.
- It does not approve, publish, or silently overwrite terms.
- It does not generate regulatory mappings.
- It does not provide model confidence scores or generated legal reasoning.
- It does not replace the customer’s own reviewers, terminology owners, or approval process.
- It does not affect the availability of the existing scanner, manual draft creation, or four-eyes approval workflow if the AI service is unavailable.
Data flow
For a request deliberately initiated by an eligible administrator, the app fetches bounded excerpts from the selected Confluence pages and sends the request to Atlassian-hosted Forge LLM. Secret-like assignments are redacted before excerpts enter the prompt. The app does not use a DailyMind-operated model endpoint for this feature. See the privacy policy (§3.5).
| Data category | Use | App persistence |
|---|---|---|
| Selected term names, occurrence counts, and page identifiers | Bound the request and link output to the administrator’s chosen findings. | Page references are stored with the proposal metadata. |
| Bounded page excerpts | Provide context for a draft definition and aliases. | Not stored. Curation records exclude prompts, excerpts, page bodies, reasoning, and raw model responses. |
| Draft term, aliases, source-page references, and model/version metadata | Enable human review, traceability, and normal draft creation. | Uncreated previews expire after 14 days. Created candidates and resulting Draft terms remain normal app records. |
Processing stays with Atlassian-hosted Forge LLM; see the privacy policy for the processor and retention position. We do not make a data-residency, model-quality, service-availability, response-time, capacity, or cost commitment for AI-assisted curation.
Third-party dependency
The feature depends on Atlassian’s Forge LLM service. DailyMind cannot control or guarantee its availability, model/version behaviour, moderation behaviour, usage limits, pricing, or Marketplace upgrade process. If the service is unavailable, the AI feature fails closed and the existing non-AI workflows remain available.
Atlassian documents Forge LLMs and their upgrade requirements in its Forge LLMs API documentation. Forge invocation constraints also vary by function type; see Atlassian Forge invocation limits.
Release and upgrade
- Forge LLM capability was added in the v5.0 major-version release (August 2026).
- Each customer’s Confluence administrator approves that upgrade, and its new data boundary, for their tenant.
- After the upgrade, eligible administrators choose whether and when to use the optional feature.
Customer controls
- Administrators choose the findings submitted for a draft request.
- Administrators and reviewers can edit or discard candidate drafts.
- The creator or last editor cannot approve the resulting term.
- A different eligible reviewer must perform the normal four-eyes approval.
Related documents
- Compliance for Confluence — approved terms, page scanning, and audit evidence for regulated teams in Confluence
- Privacy Policy — production v6 data handling, including Forge LLM (§3.5).
- Security Whitepaper — production v6 security boundary.
- App Limitations — product and platform constraints.