# Storage Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/storage
> Markdown URL: https://aitinkerers.org/technologies/storage.md
> Technology record last updated: 2026-05-18T00:47:18Z
> Generated: 2026-09-20T12:42:07Z

The definitive testing ground and authority for enterprise and consumer data storage performance.

StorageReview is the industry's premier independent laboratory for rigorous hardware benchmarking and analysis. Operating out of a dedicated facility in Cincinnati, the team puts enterprise arrays, NVMe SSDs, and high-density NAS units through real-world stress tests to provide unbiased telemetry. By covering everything from 30TB HAMR hard drives to petabyte-scale AI storage clusters, they give IT architects and enthusiasts the specific data points needed to optimize infrastructure and hardware selection.

- Official technology site: https://www.storagereview.com
- Public AI Tinkerers demos and talks: 5
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Multi-Pass Building Defect Detection: Getting a VLM to Find Facade Defects for Visual Inspections](https://dc.aitinkerers.org/talks/rsvp_3zzrUv1SHxo)

We built an AI system that turns raw building inspection photos into annotated defect reports, detecting 15 distinct pathologies (building cracks, sealant degradation, brick spalling, mortar erosion, steel corrosion, and so on) with accurate bounding boxes across facade inspections. I'll show the architecture of how we've setup the inspection image processing pipeline: the multi-pass detection architecture, the model training process, the defect annotation catalog, the eval harness we use to verify accuracy on new datasets & catch regressions. And why this was our selected way to set it up. I'll walk through the examples of real reports going from photo dump to structured outputs (where the model gets it right and where it still needs a human check).

- Event context: AI Tinkerers DC Metro - Arlington: July 23rd Meetup — 2026-07-23 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_3zzrUv1SHxo

### [Using Voice AI To Extract Subject Matter Expertise](https://seattle.aitinkerers.org/talks/rsvp_TRQ3V4xNF4A)

An AI Voice Interviewing Platform that calls the user's phone and interviews them in real-time.

- Event context: AI Tinkerers Seattle: GTM Engineering — April Meetup — 2026-04-23 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_TRQ3V4xNF4A

### [eomer: An Agentic Operating System for Data Science](https://singapore.aitinkerers.org/talks/rsvp_2G9vgEuwDJc)

eomer is an agentic operating system for data science that fine-tunes tabular foundation models on proprietary data to deliver production-ready forecasting, regression, and classification pipelines. In this demo, I’ll show how we go from raw enterprise data (CSV / DB) → automated feature handling → model selection & fine-tuning → calibrated forecasts with uncertainty → deployable outputs (API/UI) in a single workflow, without bespoke ML engineering.

- Event context: AI Tinkerers Singapore: The Agentic Future & Dev/Eng Workflows — 2026-04-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_2G9vgEuwDJc

### [Get Shit Done: De idea a SaaS en producción en 7 días con Claude Code](https://bogota.aitinkerers.org/talks/rsvp_Ibf98jRs5c4)

Voy a mostrar cómo construí KeepItX — una plataforma SaaS para captura colaborativa de fotos en eventos — en exactamente una semana usando el framework "Get Shit Done" y Claude Code como mi copiloto de desarrollo. Voy a hacer un walkthrough del código real: la arquitectura Next.js + Supabase, cómo estructuré los prompts y sesiones con Claude Code para maximizar velocidad, las decisiones técnicas que tomé (y las que delegué al AI), y el flujo completo desde el primer commit hasta tener usuarios reales pagando $99 por evento. Sin slides, puro código y terminal.

- Event context: AI Tinkerers Bogotá: El Primer Meetup de 2026 — 2026-02-26 — Bogotá
- Public talk page: https://bogota.aitinkerers.org/talks/rsvp_Ibf98jRs5c4

### [Building Knobase: Personalized AI Tutoring with mem0 Memory, ZeroEntropy RAG, and Real-Time Content Safety](https://hong-kong.aitinkerers.org/talks/rsvp_cSLy04LtLvE)

Context: Knobase powers personalized AI tutoring for 1,000+ students across various schools in Asia. The core insight we learned: teachers need AI agents they can configure and trust without writing code, and students need personalization that remembers their learning style across sessions — not just generic ChatGPT wrappers that hallucinate or give direct answers when Socratic questioning is more effective. This talk is a technical deep-dive into how we orchestrate multiple AI systems to deliver that experience at scale, walking through five implementation layers: 1. Personalization with mem0 — A hybrid memory architecture combining mem0’s semantic vector search with a local confirmed-memories table in Supabase. As students chat, we extract preferences, learning styles, goals, and challenges via regex pattern matching and prompt scoring (confidence threshold ≥ 0.85). Students confirm these memories (“Yes, I’m preparing for IB exams”), and they’re injected into every subsequent chat. A 10th-grader studying physics gets reminders about their preference for step-by-step explanations; a university student preparing for finals gets context about their exam timeline. I’ll walk through  getContextualMemoriesForPrompt()  and how we merge local + mem0 results to build a per-student profile that persists across days and subjects. 2. RAG with ZeroEntropy — Teachers upload textbooks, lecture slides, problem sets, and institutional syllabi. Document ingestion pipeline: file upload → Supabase Storage → base64 encoding → ZeroEntropy with semantic chunking (chunk_size: 1800, overlap: 200). Collections are scoped per school ( school_{id} ) so students only retrieve content their teachers authorized. Retrieval uses topSnippets queries with metadata filtering by document/knowledge IDs, plus a parallel RAG agent that expands queries and aggregates deduplicated results. This means when a Harrow student asks “What’s Newton’s second law?”, the AI cites their specific uploaded physics textbook, not generic web content. I’ll show the filter-building logic and how we resolve documents through bot → knowledge → collective → document chains. 3. Real-Time Context API — Teachers can connect external data sources (Google Sheets of upcoming assignments, Notion databases of class resources, live sports scores for a journalism class analyzing data) via webhook-based context providers. On every message, we call registered providers, AI-process the response with token optimization (60-90% reduction), and inject it alongside RAG results. Example: A history teacher at ISF Academy configured a timeline of World War II events that updates the AI’s context window in real time, so students always get era-appropriate answers. I’ll trace the full flow from  chat.context_config  → provider webhook → context processing → system prompt assembly. 4. No-Code AI Chat Builder for Teachers — Educators configure role, tone, age group (elementary/middle/high school/university), complexity, subject, language, Socratic mode toggle (forces the AI to ask guiding questions instead of giving direct answers), citation preferences, and custom instructions — all stored as  custom_details  JSON. Organization-level master prompts override per-bot settings for school-wide safety policies. I’ll show how the system prompt is assembled in 10 steps: master prompt → bot intro → RAG context → memory context → custom instructions. A teacher creating a “Socratic Math Tutor” for 8th graders clicks 6 dropdowns and writes 2 sentences of instruction; the system generates a 2,000-token prompt behind the scenes that enforces age-appropriate language, refuses to solve homework directly, and cites only the uploaded textbook. 5. Education Safety Stack — Real-time prompt scoring (Clarity/Specificity/Task Definition/Context/Structure on a 0-100 scale) via a Supabase Edge Function runs on every student input. Content flagging across 7 categories (sexual content, bullying, profanity, racial bias, political sensitivity, harmful advice, PII detection) plus custom organization-defined flags (e.g., Harrow added “exam cheating detection”). A daily digest cron emails flagged messages to designated safety managers. Student interest keywords and learning purpose analysis are extracted as a side effect of scoring and fed back into mem0, creating a feedback loop where the AI becomes more personalized the more the student uses it. We’ve processed 16,000+ messages since December 2025 with this stack in production. ** Code walkthrough will focus on the chat route orchestration (~3,700 lines) that ties all five layers together in a single request lifecycle. No slides — just live code, architecture diagrams on a whiteboard, and real examples from our production deployment.

- Event context: AI Tinkerers Hong Kong & GBA: Using AI as a Superconductor for Learning — 2026-02-26 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_cSLy04LtLvE

## Related Technologies

- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [React](https://aitinkerers.org/technologies/react) ([Markdown](https://aitinkerers.org/technologies/react.md)) — 219 public demos
- [Supabase](https://aitinkerers.org/technologies/supabase) ([Markdown](https://aitinkerers.org/technologies/supabase.md)) — 90 public demos
- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [Vercel](https://aitinkerers.org/technologies/vercel) ([Markdown](https://aitinkerers.org/technologies/vercel.md)) — 48 public demos
- [Auth](https://aitinkerers.org/technologies/auth) ([Markdown](https://aitinkerers.org/technologies/auth.md)) — 1 public demo
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Azure](https://aitinkerers.org/technologies/azure) ([Markdown](https://aitinkerers.org/technologies/azure.md)) — 10 public demos
- [Azure Blob Storage](https://aitinkerers.org/technologies/azure-blob-storage) ([Markdown](https://aitinkerers.org/technologies/azure-blob-storage.md)) — 1 public demo
- [Backend](https://aitinkerers.org/technologies/backend) ([Markdown](https://aitinkerers.org/technologies/backend.md)) — 7 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 173 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Claude Sonnet](https://aitinkerers.org/technologies/claude-sonnet) ([Markdown](https://aitinkerers.org/technologies/claude-sonnet.md)) — 20 public demos
- [Database](https://aitinkerers.org/technologies/database) ([Markdown](https://aitinkerers.org/technologies/database.md)) — 8 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos
- [Edge Functions](https://aitinkerers.org/technologies/edge-functions) ([Markdown](https://aitinkerers.org/technologies/edge-functions.md)) — 1 public demo
- [FastAPI](https://aitinkerers.org/technologies/fastapi) ([Markdown](https://aitinkerers.org/technologies/fastapi.md)) — 181 public demos