The Therapeutic Program Architect
Give it any disease — common or genetic/rare — and it runs a full, human-in-the-loop drug-development program: from unmet need and patient priorities, through data- and literature-mined target and modality selection, AI/ML design and in-silico pressure-testing, to scientific, regulatory, and commercial strategy. It stops and asks you at every consequential decision.
This is for any disease — not just EoE
The disease, target, and modality are all parameters resolved from data and your decisions, not hard-coded. The same modality router that produced a tolerizing vaccine for eosinophilic esophagitis produces a ligand-trap, antibody, or small molecule for another disease depending on the target biology. If your community has a disease and a question, this is built for you.
Ten stages, threaded through one dossier
A single JSON program dossier is the source of truth for a whole run — disease, scope, every decision and who made it, per-stage artifacts, gate status, and open questions. A program can be paused, resumed, and audited.
- Indication & unmet need Epidemiology, biology, standard of care, and precedent.
- Patient priorities / PFDD What patients actually want fixed — with an optional community survey.
- Literature + competitive pipeline Mechanism map plus who is developing what, and why they succeeded or failed.
- Data mining → targets Omics meta-analysis and single-cell → ranked druggable targets.
- Target & modality selection The pivotal fork: a scored rubric, then you confirm the pick.
- Design & pressure-test Modality-routed AI/ML design plus in-silico validation.
- Scientific development plan AI-to-first-in-human assay cascade, CMC, biomarkers.
- Regulatory strategy FDA / EMA path, designations, endpoints.
- Commercial & financing TAM/SAM/SOM, whitespace, financial model, and the Ask.
- Deliverables & synthesis Business plan, scientific plan, deck, manuscript, peer review.
Human-in-the-loop by design
The pipeline never silently commits a target, modality, endpoint, price, or go/no-go. It stops at named gates and asks a structured question with its recommendation and options.
Block until you answer
- Scope lock
- Whitespace confirm
- Target / modality lock
- Design go / no-go
- Financing assumptions
- Final review
It proposes; you can veto
- Priority rank
- Target evidence
- Regulatory assumptions
- Any low-confidence flag becomes a recorded open question — not a confident-sounding assertion
Validated beyond EoE
IPF
Idiopathic pulmonary fibrosis. The modality router lands on a ligand-trap / antibody / small molecule path driven by the target biology — not the tolerizing vaccine EoE called for.
SMA (genetic)
Spinal muscular atrophy. Exercises the genetic/rare archetype branch — a monogenic, mechanism-driven program with a different modality decision tree.
EoE
Eosinophilic esophagitis. The complete run behind Project Tolera — a personalized pMHC-II tolerance vaccine, end to end.
How to install and use it
It comes in two pieces: drug-program-orchestration (the conductor skill) and the Therapeutic Program Architect (a specialist agent that preloads the skill and has full access to the skill catalog and all data/regulatory connectors).
- Get the repository Clone or download from GitHub:
git clone https://github.com/ruthannepai-tech/therapeutic-program-architect.git - Add it to Claude Science Drop the skill folder into your skills directory, or publish it via the skill SDK. The specialist profile registers the orchestration skill and its connectors.
- Switch to the specialist In the Claude Science session-config popover, choose the Therapeutic Program Architect specialist (or accept the switch prompt).
- Run a program Say it in one line:
The orchestrator initializes a dossier and walks the ten stages, stopping at each gate.Run the drug program for <your disease>.
No specialist switch? Any agent can run it
Load the drug-program-orchestration skill
and run the pipeline for <your disease>.
Requirements & caveats
The design stage (Stage 6) benefits from a GPU compute target — the orchestrator checks for one and runs the CPU-feasible parts or defers design if none is configured. Connector calls (ClinicalTrials.gov, Open Targets, FDA, GEO/PRIDE, ChEMBL) run automatically inside the specialist. All forward-looking scientific, regulatory, and commercial statements are development hypotheses — not established results, medical advice, or guaranteed outcomes.