ellora_briefs_fetch_active
ChatGPTList every active writing brief for your team, with their writing_brief_id — the IDs usable with ellora_session_start — plus each row's nested writing_brief_json, which can be passed back to ellora_session_start verbatim.
ellora_briefs_fetch_by_id
ChatGPTConfirm one writing brief is active and usable by writing_brief_id, returning its name. Only active briefs are returned.
ellora_context_capture
ChatGPTCapture a context document from this team's content session. It is always saved disabled; an admin must activate it before it can affect rewrite prompts.
ellora_context_fetch_active
ChatGPTList active context documents for your team. Returns metadata only; use ellora_context_fetch_by_id for the full document.
ellora_context_fetch_by_id
ChatGPTFetch the full body of one active context document for your team. Read-only — the fetch bumps only an internal retrieval counter, never the document content, kind, source, or status.
ellora_learn_from_accepted_rewrite
ChatGPTStore user-approved writing rules from an accepted rewrite. The caller must supply concise, explicitly approved rules; Ellora does not infer subjective preferences. This does not run or require ellora_review.
ellora_positioning_recommendations
ChatGPTReturn recommendation-only positioning and messaging guidance from this team's active positioning profile, approved context, and learned voice preferences. Read-only — selecting context bumps only an internal retrieval counter, never any governed field.
ellora_profile_create
ChatGPTCreate a saved voice profile for this team from writing samples, and make it active. Use this when the team has no active voice profile yet — check ellora_profiles_fetch_active first. Requires a team admin. Returns the new voice_profile_id, usable with ellora_session_start.
ellora_profiles_fetch_active
ChatGPTList every active voice profile for your team, with their voice_profile_id — the IDs usable with ellora_session_start.
ellora_profiles_fetch_by_id
ChatGPTConfirm one voice profile is active and usable by voice_profile_id, returning its name. Only active profiles are returned — the same requirement ellora_session_start enforces.
ellora_review
ChatGPTAnalyze this content against the voice profile/writing brief fixed by ellora_session_start. Returns findings plus a convergence hint — follow next_action. When mandatory findings are open, the response includes rewrite_guidance: rewrite the content yourself and call ellora_review again before showing anything to the user. Once a call passes and it is not the session's first, this also automatically verifies the result against the session's original content for regressions and, on success against a saved voice profile, teaches the profile from it. Stop and deliver once you see a verification block with passed: true, or once next_action says diminishing_returns.
ellora_session_start
ChatGPTCall this first, before showing the user any draft, whenever you are writing or editing prose that should match this team's brand voice or a writing brief. Fixes the voice profile and writing brief for the whole session — every ellora_review call in it is checked against these same values. A writing brief is required: pass writing_brief_id (pick one via ellora_briefs_fetch_active/_by_id) or writing_brief_json (the nested object ellora_briefs_fetch_active returns, passed back verbatim, or a brief you construct for this content) — never omit both. Returns a content_session_id that must be passed to every subsequent call for that same piece of content.