AccurateAI · open source

AI products,
built in plain sight.

Open-source AI for healthcare access, enterprise governance, and clinical decision-support. Each project ships with its adversarial eval, its safety net, and its source — by Sankar Subbayya.

Projects

  • Delphi headline slide — 13.3% to 79.5%, +66.2 pp shift after a single news shock.

    Delphi

    Google I/O Hackathon · May 2026

    Synthetic populations as a computational substrate. You ask any question — 'will the Fed cut rates?', 'pretest this tagline', 'stress-test this decision' — and dozens of Gemini 3.5 Flash sub-agents, each role-playing a different American persona generated from US Census demographics and grounded in live web, reason in parallel. In ~60 seconds you get a probabilistic forecast, the strongest reasons for and against, where demographics diverge, and a striking outlier quote — synthesized into a Wall Street Journal–style summary by a final Gemini call. Live-demoed with a sixty-percentage-point swing on one news shock.

    Try demo →Source ↗
  • Path to Care · AMD Developer Hackathon project poster.

    Path to Care

    AMD Developer Hackathon · May 2026

    Multimodal, agentic triage decision-support for rural healthcare in the Global South. A phone photo plus a typed narrative becomes a top-3 condition guess, a Red/Yellow/Green urgency, and a structured pre-visit SOAP for the clinic doctor — contextualized by village distance, cost, and harvest season. Built in 24 hours on a single AMD Instinct MI300X. Never diagnoses.

    Try demo →Source ↗
  • Sentinel Health · Gemma 4 Good Hackathon project poster.

    Sentinel Health

    Gemma 4 Good Hackathon · May 2026

    Offline triage for community health workers in low-resource settings. Multimodal Gemma 4 + a deterministic safety layer + a WhatsApp handoff to the hub physician — runs entirely on a clinic laptop, no internet. Scoped to five grassroots emergencies: trauma, poisoning, snake bite, MI, stroke.

    Try demo →Source ↗
  • Agent Sentinel · AI & Big Data Expo project poster.

    Agent Sentinel

    AI & Big Data Expo · San Jose · May 2026

    Governance plane for enterprise AI agents. Gates every tool call, signs the audit trail with hash-chained HMAC, and meters per-BU spend. Built on Gemini 2.5 Flash + Pro with Cached Content over full policy documents. The control plane between agentic pilots and production.

    Try demo →Source ↗
  • AgentQED · Zero to Agent Hackathon project poster.

    AgentQED

    Zero to Agent Hackathon · Vercel × DeepMind · March 2026

    From an idea by Ganesh Sankar (UC Berkeley). Translate a math proof in plain English, voice, or a photo of handwritten work into Lean 4, then formally verify it with the real compiler in an isolated Firecracker microVM. Gemini 3.1 Pro writes the Lean, Vercel Sandbox runs it, and on rejection the agent reads the compiler's error and edits the proof — up to twelve times — until it typechecks. Compiler-verified, not vibes-verified.

    Try demo →Source ↗

What ties them together

Five projects, one posture: AI that names its own limits.

Path to Care never produces a diagnosis. Sentinel Health never overrides a red flag. Agent Sentinel never lets a model bypass its policy gate. Delphi never claims certainty without showing where its personas disagreed. AgentQED never accepts a proof unless the Lean compiler accepts it first. The safety layer is code, not a disclaimer.

Every project ships an adversarially-authored test set and a measurable safety target — zero false-negatives on Red triage for Path to Care, zero unauthorized tool calls for Agent Sentinel, reproducible demographic-divergence reporting for Delphi — plus a single-command demo. If you can't reproduce the claim on the repo, the claim doesn't count.