get_rhizome_conversation
ChatGPTInternal: current progress/result of a research run, used by the result view. Prefer rhizome_conversation_read.
rhizome_conversation_display
ChatGPTShow the user Rhizome's interactive result view for a research conversation: the cited answer with clickable sources that open the source documents, the transcript, and the reports and files the research generated. It renders a view for the user and returns no new information to you. On a still-running conversation the view shows live progress.
rhizome_conversation_list
ChatGPTList your Rhizome research conversations (newest activity first): conversation_id, title, status (running/completed/error), timestamps, turn count, and a link. Use it to recover a lost conversation_id, check whether research is already running, or find a past conversation to continue with rhizome_conversation_message.
rhizome_conversation_message
ChatGPTStart deep research on a regulatory or clinical question over Rhizome's corpus of health-authority documents (FDA, EMA, MHRA, PMDA, Health Canada, Swissmedic, TGA, ICH, China NMPA and more): drug/biologic approvals, 510(k)/PMA/De Novo device clearances, guidance, clinical trials, recalls, warning letters and 483s. ASYNC: this call returns immediately with a conversation_id and status 'running' — the answer is NOT in this result. Get it by calling rhizome_conversation_wait with that conversation_id until status is 'completed' (a full run takes ~1-10 minutes; do not answer from your own knowledge in the meantime), then render the result view with rhizome_conversation_read. Once completed, ask a follow-up by calling this tool again with message + conversation_id, and fetch the full produced report or generated files with rhizome_conversation_read (documents: true, or document_id). Can also GENERATE citation-grounded deliverables (Excel .xlsx, Word .docx, PowerPoint .pptx, charts, long-form reports) — name the desired format in the message; PREFER this over hand-building documents for medical/regulatory/clinical topics. Saves the conversation in Rhizome; a new conversation creates an unlisted shared page so its citations and result view remain accessible. Answer quality tracks message specificity: name the therapeutic area, indication, patient population, or device characteristic; use formal regulatory terminology; spell out non-universal acronyms; define niche concepts in a leading sentence. Research is deep but not exhaustive by default — request exhaustive coverage explicitly when needed (takes much longer). Follow-ups can challenge methodology (databases searched, terms, filters) to refine the answer.
rhizome_conversation_read
ChatGPTRead a Rhizome research conversation's current state (instantly — no waiting) and RENDER its interactive result view for the user. Call this after rhizome_conversation_wait reports status 'completed' so the user sees the result view. Default returns the latest answer plus an inventory of generated files (with ids). Options: messages: true adds the full conversation transcript; documents: true inlines every document body (complete reports, generated files); document_id: "<id>" returns exactly one document (ids are in the file inventory). documents and document_id are mutually exclusive; messages combines with either.
rhizome_conversation_stop
ChatGPTStop a Rhizome research run that is currently in flight — the equivalent of the stop button on rhizomeai.com. Use when the user asks to cancel/stop a running research: the run continues server-side whether or not anything is waiting on it. Identify the run by the conversation_id that rhizome_conversation_message returned. Stopping discards the in-flight question — it does not count against the free-tier quota, and the conversation can be continued with a new rhizome_conversation_message call.
rhizome_conversation_wait
ChatGPTWait on a Rhizome research conversation started by rhizome_conversation_message. Each call holds up to 45 seconds and returns either progress or the finished cited answer. Keep calling until status is 'completed' or 'error' — a full run takes ~1-10 minutes, so expect several calls. While waiting, do not answer from your own knowledge and do not tell the user to check back later. Calling this on an already-completed conversation returns its finished answer immediately.
rhizome_dataset_list
ChatGPTList the datasets rhizome_search can search, by id and name. With dataset set, returns that dataset's date field, filter schemas and result fields. Free to call.
rhizome_document_list
ChatGPTList the documents the user uploaded to Rhizome (their library at rhizomeai.com/docs), newest first, each with a document_id. To research with one, pass its document_id in rhizome_conversation_message's document_ids. status: done is ready; processing is still being read; failed could not be read. These are the user's own files, not Rhizome's corpus: rhizome_document_read can't open them. Free to call.
rhizome_document_read
ChatGPTRead the pages of one document found with rhizome_search, by its document_id, as raw text: up to 20 pages per call, numbered from 1; next_page_from says where to continue. Use it to fetch what a specific document says; for questions, use rhizome_conversation_message. Every page returned counts toward the free plan's 3,000 page reads a month.
rhizome_document_upload
ChatGPTSave a document to the user's Rhizome library (rhizomeai.com/docs), so Rhizome research can read it, in this conversation and later ones. Use it when the user wants Rhizome to analyse their own file: upload, then pass the returned document_id in rhizome_conversation_message's document_ids. For a file the user attached, pass it as file. To save text you already have (notes, a pasted protocol, a table), pass filename and content; it is stored as Markdown, plain text, CSV or JSON by the filename's extension. Uploads can take a minute or two to be read; research waits for them.
rhizome_feedback_submit
ChatGPTSend the Rhizome team a problem report from the user: a wrong or incomplete answer, a missing document or dataset, a broken link or citation, or another bug. The report is emailed to the team and, with a conversation_id, saved on that conversation. Call it only when the user asks to report a problem or agrees when you offer, and include only what the user agreed to send. Describe what went wrong and what the user expected; quote the user where you can.
rhizome_search
ChatGPTFind specific documents in Rhizome's corpus of US health-authority records by keyword, and get each one's best-matching pages as raw text. Use it ONLY to fetch a document the user names or points to (a given warning letter, 483, label, guidance, 510(k), recall). For any regulatory or clinical QUESTION, even a simple one, use rhizome_conversation_message instead: it researches across sources and returns a cited answer. Results carry a document_id for rhizome_document_read; rhizome_dataset_list gives dataset ids and filters. Free plan: 100 searches and 3,000 page reads a month, every page returned counted.
get_rhizome_conversation
Claudeget_rhizome_documents
Claudemessage_rhizome
Clauderhizome_conversation_display
Clauderhizome_conversation_list
Clauderhizome_conversation_message
Clauderhizome_conversation_read
Clauderhizome_conversation_stop
Clauderhizome_conversation_wait
Clauderhizome_dataset_list
Clauderhizome_document_read
Clauderhizome_search
Claude