Stop guessing which reviewer criticism matters most. The Grant Pivot Engine extracts critiques, maps them to your proposal, drafts your response, and simulates your study-section review—all on your own hardware.
NIH resubmissions are high-stakes and time-consuming. GPE gives PIs and their teams an AI co-pilot that runs entirely on your own workstation.
Understand every reviewer criticism in minutes, not days. Get a structured breakdown mapped directly to the sections of your proposal that need the most work.
AI-generated "Introduction to Resubmission" drafted in your PI's voice, grounded in their prior funded work. Edit, refine, and submit with confidence.
Full audit trail of every action. Air-gap mode keeps sensitive proposal text entirely off the internet. Compliance-ready from day one.
Runs on a single on-premises workstation with no cloud API calls for proposal data. Your IRB-sensitive content never leaves your network.
Five steps take you from raw reviewer feedback to a polished resubmission introduction, with a simulated study-section check before you finalize.
Start a new project for your grant application. Provide the PI
name and NIH mechanism (R01, R21, etc.)
to set the context for all AI operations.
Upload your original proposal (PDF/DOCX/TXT), the NIH summary statement, and any prior funded work to establish your PI's writing voice.
The engine parses your summary statement and extracts every reviewer criticism—severity-ranked and automatically mapped to the specific proposal sections they target via RAG.
One API call generates a structured "Introduction to Resubmission" that addresses all critiques in the correct NIH format, written in the PI's voice.
Before submitting, run a simulated NIH study-section review of your draft. Receive reviewer-style scores and comments so you can iterate before the real deadline.
Five integrated capabilities that take your NIH grant from rejected to fundable—with no data leaving your network.
Automatically parse NIH summary statements and extract every reviewer criticism. Each critique is classified by the standard NIH review criterion and assigned a severity level so you know where to focus first.
Each extracted critique is embedded and searched against your original proposal using local vector search. The engine surfaces the exact proposal passages reviewers likely had in mind—no manual cross-referencing required.
Generate a complete "Introduction to Resubmission" that addresses every reviewer concern. The LLM retrieves your PI's prior funded work to match their writing voice, producing a draft that sounds like them—not a generic chatbot.
Before your real submission deadline, test your draft against a simulated NIH study section. Receive reviewer-style priority scores and detailed comments—so you can iterate until you're confident in your resubmission.
Search NIH RePORTER and Grants.gov for current funding opportunities matching your research area. Outbound requests are limited to allow-listed federal APIs—your proposal text never leaves the box.
Every action—project creation, document ingestion, critique extraction, drafts, and simulations—is logged to a tamper-evident SQLite audit log. Essential for institutional compliance and reproducibility.
Designed for institutions that cannot afford to send sensitive grant proposals to third-party AI services.
Set GPE_AIR_GAPPED=1 to block all outbound HTTP
traffic. Critique extraction, response drafting, and review
simulation continue to work with zero internet access.
Runs llama3.3:70b via Ollama on the GX10's NVIDIA GB10 GPU. No OpenAI, Anthropic, or other cloud API keys are required or used.
When not air-gapped, only api.reporter.nih.gov and
api.grants.gov are reachable. Funder searches send
keywords only—never proposal text.
All data—documents, critiques, drafts, vectors—lives in a local
SQLite database and NumPy array files under GPE_DATA_DIR.
No cloud sync.
Place any reverse proxy (Shibboleth, oauth2-proxy) in front. The
engine reads the authenticated user from the
X-Remote-User header for per-action audit logging.
Every API action is written to a structured audit log with timestamp, authenticated user, action type, and detail payload. Meets most institutional audit requirements.
A Cloudflare Worker serves the static front-end from the edge while routing API calls through an encrypted tunnel to your on-premises GX10.
cloudflaredBring up the full hybrid stack—on-premises LLM backend plus Cloudflare edge—in an afternoon.
Run the one-line installer on your ASUS Ascent GX10. It installs
Ollama, pulls llama3.3:70b and
nomic-embed-text, sets up the Python venv, and
registers a systemd service at http://<gx10-ip>:8800.
On the GX10, install cloudflared, create a named
tunnel, and configure it to forward to localhost:8800.
Start the tunnel as a systemd service for automatic reconnection.
From the cloudflare-worker/ directory, deploy with
Wrangler. Set the TUNNEL_BASE_URL environment variable
in the Cloudflare dashboard to point to your tunnel hostname.
Hit the public Worker URL to confirm the static site loads, then
check /api/status to confirm the tunnel reaches
the GX10 backend. You're ready to create your first project.
Run the backend in mock mode on any laptop with no GPU or model
server required: GPE_MOCK_LLM=1 uvicorn app.main:app --port 8800.
All endpoints return deterministic canned responses—perfect for CI
pipelines and UI development.
GPE is an open, internal research tool. Deploy it on your GX10 today and take the guesswork out of your next NIH resubmission cycle.