Lutfiya Miller (Drfiya)

Board-certified toxicologist (PhD, DABT) and AI builder. Co-founder of ScienceExperts.ai. Miller & Müller: 5 hackathon prizes in 2026

United States
Website
GitHub
Twitter
LinkedIn

Errands — Errands

A Strands agent that runs real errands end to end, dinner, subscriptions, a car service with a vetted driver, on one ladder of trust that only interrupts you for money, keys, or a stranger.

Interlock — Interlock

A pull-request gate that blocks the data change which would silently break your production ML model — it walks DataHub lineage and replays the real model to prove it.

Recall — Recall

A lineage native pre-mortem agent for production ML which reads DataHub's causal graph backwards to find the models that are about to break, and writes the diagnosis back into DataHub.

deadreckon — deadreckon

An agent that walks DataHub's ML lineage graph to catch silent model failures - and tells you, separately, what it couldn't check at all.

Inner Life - The catalog's biographer — Inner Life - The catalog's biographer

An agent that reads your DataHub catalog every day, writes what it found in four voices people actually read, and writes it back so the next person inherits it.

DATAFORENSIC AI — DATAFORENSIC AI

The organizational memory engine for DataHub: an agent that investigates data incidents, proves the root cause with evidence, and turns every resolution into reusable knowledge.

DevGuard Enterprise — DevGuard Enterprise

A closed-loop incident agent for DataHub: proves root cause from the lineage graph, refuses when the evidence is insufficient, and writes verified incident knowledge back as first-class metadata.

BLASTRADIUS — BLASTRADIUS

Most security alerts about your data pipelines don't matter. This tells you which five out of a thousand do

Gatehouse — Gatehouse

DataHub gives agents context. Gatehouse makes context decide what they may do: an MCP gateway that checks every agent tool call against live graph facts before it runs.

RIFT — git diff for business logic — RIFT — git diff for business logic

Two dashboards disagree about revenue. RIFT proves exactly why it rewrites the SQL, executes it, and measures what each clause is worth in dollars — then writes the answer back to DataHub.

ML Guard — ML Guard

ML Guard is a production ML agent that uses DataHub’s context graph to detect target leakage and stale-model risk, trace every finding through column lineage, and write evidence back to DataHub.

RippleProof — RippleProof

Renames a warehouse column without breaking what depends on it: reads DataHub lineage, writes dbt repairs across every affected repo, proves they build, and refuses when it cannot prove them safe.

ContextSeal — ContextSeal

Every data change ships with proof, not confidence. ContextSeal uses DataHub context to block risky schema changes and generate safe, reviewable migration packages.

Culprit: a stack trace for model decay — Culprit: a stack trace for model decay

A stack trace for model decay. Give it a degraded model and a vague complaint, and it walks DataHub's ML lineage to the column that broke it, prices the damage in dollars, and opens the PR.

Hindsight — Hindsight

The on-call agent that gets cheaper every time it runs: it files each postmortem inside DataHub, so the next incident starts from the last one. Measured: 20 tool calls cold, 15 warm.

Schema-Drift Auto-Repair Agent — Schema-Drift Auto-Repair Agent

When an upstream column is renamed, retyped or dropped, this agent uses DataHub's column-level lineage to find exactly what breaks, repairs the code, and ships the fix as a reviewed pull request.

Project Blackbox — Project Blackbox

Autonomous data incident repair, with proof!

DocuMorph AI - ERNIE Multimodal Document Transformer — DocuMorph AI - ERNIE Multimodal Document Transformer

Transform static PDFs into dynamic, responsive, and interactive HTML webpages with AI-powered semantic injection and multimodal vision analysis.

ConfidFit — ConfidFit

ConfidFit adds YouCam generative apparel try-on to Shopify. Shoppers preview looks from a photo; merchants run a real product with metering, analytics, and honest labels.

KeepMe — KeepMe

KeepMe makes AI virtual try-on trustworthy. Shoppers control what can change, detect unwanted changes to their appearance, repair visual drift, and receive proof before approving the result.

ShadeSpan — ShadeSpan

The same t-shirt is obvious on one customer and nearly invisible on another. ShadeSpan renders every garment on every skin tone with YouCam VTO and grades the colours that vanish — before launch.

Aloud — Aloud

Beauty, aloud. The first beauty AI a blind shopper can use alone, screen off. Built on the YouCam Skin Analysis API.

SalesShortcut — SalesShortcut

A comprehensive AI-powered Sales Development Representative (SDR) system built with multi-agent architecture for automated lead generation, research, proposal generation, and outreach.