TTMNG Pharmaceutical assist

View saved version →

---
name: compare-use
description: Inspect current TTMNG herb–medicine evidence for any accepted scientific taxon and selected foreign product, separating documentary clinical contexts, source-bound constituent mechanisms, recorded research and unresolved applicability.
---

Select the exact current accepted herb taxon and exact foreign product through `ttmng_reference_catalog`. Call `ttmng_reference_compare` using their exact reference_ids, or scientific_name and presentation_id. Registered pairs are coverage, not an allowlist: any accepted current taxon may be compared with any selected required product. A missing or held identity needs only an indispensable choice; Thai/fuzzy names cannot select taxa.

Read returned documentary_contexts and their exact clinical record_ids with `ttmng_evidence_record`. Follow pagination. Preserve whether a study used an isolated constituent, enhanced formulation, whole-herb preparation, formula, rescue medicine or merely named a class/ingredient; study-product omissions do not establish an exact selected-product trial. Preserve dose, route, duration, population, endpoints, denominators, negative results, source dates and original restrictions. Existing human content review is limited to its exact source facts and does not authenticate material or transfer to chemistry.

Read nonclinical_paths separately. Each path links exact sample occurrence, isolated-molecule experiment and a medicine role through explicit compound/target records; use read_record_ids to inspect all three. This overlap supports a source-bound hypothesis only. Keep analytical quantities/calibration/n, assay system/concentration, part/preparation, contradictory findings and human exposure gaps. A common enzyme/target is not a measured net clinical interaction, probability, magnitude or validated treatment dose. Do not calculate patient-specific adjustments, declare safe co-use, substitute medicines/herbs or generalize across preparations.

Use `ttmng_evidence_question` for the actual scoped question and inspect returned research history before searching. Existing adequate evidence is used without repeating a search. A genuinely unanswered question may use available host primary-source tools, with exact scope/access/negative findings retained; this remote reader performs no new network research or canonical registration. State a missing tool/access limit, and never claim research was performed/saved/reviewed when it was not.

Use `ttmng_evidence_batch` only for bounded independent current-tool reads. An empty documentary/path result is a selected-data gap, not no interaction, safety or worldwide absence. The service does not expose legacy 1.2 data tools, internal owner answers or private files. Ordinary users require server-side owner approval; provisioned OpenAI reviewers have permanent account access. Use `ttmng_reference_status` for actual current counts/version.

View saved version →

---
name: inspect-herb
description: Read current TTMNG scientific identity, material, clinical, constituent and registered analytical research across the full current herbal registry, preserving exact preparation and evidence limits through the authenticated project service.
---

Use `ttmng_reference_catalog` kind=herb, with pagination, to select the exact current scientific identity/rank and reference_id. Names follow dated foreign taxonomy evidence. Thai, mixed, transliterated, fuzzy and historical names cannot select a taxon. Ask only for the indispensable scientific identity when it is missing; an unplaced identity remains held. Never transfer evidence to another species, rank, plant part, preparation or source sample.

Read `ttmng_reference_answer` for the chosen reference. Use section=clinical, materials, constituents or research for focused pages; section=profile exposes paginated profile fields. Follow next_offset and read exact record_ids through `ttmng_evidence_record`; independent reads may use `ttmng_evidence_batch`. Use `ttmng_evidence_question` for a scoped question and inspect its existing facts and research history before a new search.

Answer from the actual source scope. Separate current taxonomy from the source-reported historical taxon; material documentation from project authentication; human component/formulation trials from whole-herb evidence; constituent occurrence/quality markers from experimental mechanisms or clinical activity. Preserve solvent/extraction, route, population, reported quantities, units, denominator, assay/calibration, analytical n/precision, source versions/locators, negative results and table/text conflicts. Unknown calibration or denominators remain unknown. Oil peak area, solution concentration, extract mass and plant mass are not interchangeable. Voucher/botanical identification reports are source observations, not a project-authenticated consumed material.

All existing current records and registered research are available through this reader; the corpus remains partial where the evidence is partial. A missing clinical record or incomplete chemical profile is not worldwide absence or safety. Do not infer complete chemistry, pharmacobotany/dossiers, treatment dose, co-use safety or substitution. Do not request another clinical answer for unchanged already-reviewed content.

Reuse a sufficiently answering source/history without research repetition. Research a real gap only with actual available host primary-source tools and preserve the exact scope and access limits. The backend performs no new web searches and cannot register canonical findings. Do not claim saved results or a received clinical review from retrieval.

All data calls require approved access; provisioned OpenAI reviewer entitlement is permanent. Client flags cannot grant access. Do not invoke legacy 1.2 tools or expose source files, owner replies or credentials. Read actual counts and snapshot date from `ttmng_reference_status`.

View saved version →

---
name: inspect-medicine
description: Read and explain current TTMNG foreign medicine evidence across all 243 selected families, with exact products, source citations, original conditions and recorded research through the authenticated project service.
---

Use the current project tools, beginning with `ttmng_reference_catalog` kind=medicine and its page cursor. It covers all 243 selected families, with exact required targets and separately labelled supporting products. Select the exact reference_id/presentation_id from the catalog. Preserve ingredient/salt/strength basis, form, route, jurisdiction and identifier. Do not transfer a source to another formulation or use a Thai product as a current foreign target.

Read `ttmng_reference_answer` and follow next_offset when the requested scope needs further pages. Use `ttmng_evidence_record` for exact record_ids and `ttmng_evidence_batch` for bounded groups of independent reads. For an actual evidence question, use `ttmng_evidence_question` with the exact selection and relevant topic. Inspect the returned facts, original conditions, citations and recorded research before proposing any new search. Request only an indispensable unresolved product/context choice; no extra source, name, chemistry, release or repeated clinical approvals.

Lead with what the sources support and cite their exact dated versions. Preserve population, route, dose/formulation, renal/study/withdrawal limits, negative results, source conflicts and missing fields. A source-labelled regimen is reference evidence, not a patient-specific prescription or dose-adjustment instruction. Do not infer latest whole-PI coverage, current market stock, interchangeability, co-use safety or an unrecorded pathway from a family completion count.

When the existing evidence answers the question, use it without repeating research. For a real remaining gap, inspect recorded search scope/outcomes first and use available host primary-source tools if appropriate. The remote reader itself performs no new searches or canonical writes; state tool/access limits and do not claim new results were saved or reviewed. Historical ALTACE/LUPIN context retains its own conditions and never substitutes for the required TRIATEC France target.

All data calls require server-side approved access. Provisioned OpenAI reviewers have permanent account entitlement; ordinary users require owner approval. Never request passwords in chat, trust caller role flags, read private authoring files or invoke legacy 1.2 tools. `ttmng_reference_status` reports this release's actual counts/date and disabled legacy data dispatch.