SBIR Phase I Overview

PromptGenix LLC · Women & Minority-Owned · Contact: dohoon.kim1@icloud.com
The problem

Biomedical data generation outpaces scientific decision-making.

NIH-funded programs generate large volumes of multi-modal biomedical data and publications, yet a core bottleneck remains: converting heterogeneous evidence into ranked hypotheses, clear uncertainty, and concrete next-step decisions. Teams often rely on fragmented tools, ad hoc scripts, and scarce expert time, leading to slow turnaround and inconsistent reproducibility.

The innovation

PromptGenix: an evidence-weighted hypothesis intelligence engine.

PromptGenix integrates public biomedical datasets and literature into a traceable decision workflow that produces testable hypotheses with confidence ranking and explicit evidence links. The system uses statistical and Bayesian methods to quantify uncertainty, while LLMs are constrained to explanation and synthesis under strict traceability guardrails.

What is new (technical)

  • Evidence objects: standardized representation of signals from public datasets and literature
  • Probabilistic ranking: statistical scoring + Bayesian updating to compute posterior confidence
  • Traceability: every hypothesis includes “why” and links to supporting/conflicting evidence
  • LLM guardrails: narrative generation is evidence-bound (“no evidence → no claim”)
Bayesian confidence Calibration Citations Audit-friendly

SBIR Phase I scope

  • Build: validated prototype that generates ranked hypotheses and reviewer-ready reports
  • Validate: traceability, reproducibility across reruns, and usefulness for study decisions
  • Measure: time-to-hypothesis, rerun consistency, and pilot “useful” ratings
  • Deliver: HTML/PDF artifacts suitable for review and partner discussions
Boundary: Phase I evaluation uses public datasets only (e.g., GEO, SRA, FlowRepository) to avoid IP/data-use constraints.
Why it matters

Faster, more rigorous science—without requiring more expert bandwidth.

PromptGenix helps research teams move from “outputs” to “decisions” by producing ranked hypotheses with transparent uncertainty. This enables clearer experimental planning, more reproducible interpretation, and improved reviewer confidence in how conclusions were reached.

Phase II path: Phase I de-risks the core decision engine; Phase II scales to broader modalities, multi-site usage, and secure deployments for real-world partner settings.