# SQL Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/sql
> Markdown URL: https://aitinkerers.org/technologies/sql.md
> Technology record last updated: 2026-02-22T16:48:56Z
> Generated: 2026-09-22T09:48:41Z

SQL (Structured Query Language) is the standard language for managing and manipulating data in relational database management systems (RDBMS).

SQL, or Structured Query Language, is the essential tool for handling structured data: it’s the standard for RDBMS. Use it to execute core data operations: `SELECT` to retrieve specific records, `INSERT` to add new rows, `UPDATE` to modify existing data, and `DELETE` to remove it. This language is critical across all major platforms (MySQL, PostgreSQL, Microsoft SQL Server, Oracle), ensuring data integrity and enabling complex joins across multiple tables. Every data professional needs fluency in SQL; it’s the bedrock of modern data management.

- Official technology site: https://www.w3schools.com/sql/default.asp
- Public AI Tinkerers demos and talks: 17
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Watch a 4B browser model turn your boring tasks into a SKILL.md](https://nyc.aitinkerers.org/talks/rsvp_8SMqUh4VL-U)

A Chrome extension that captures browsing activity into local browser database, then runs Gemma 4 (4B) entirely in-browser via WebGPU to analyze cross-app workflows. No data leaves the browser. Live demo: the model queries my real browsing data, identifies that I was filing invoices from gmail to Google Drive folder - reconstructing intent from copy/paste patterns, typed text, and app switching. Try at assete.ai.

- Event context: NY Tech Week Demo Day ft PostHog, Convex, Veris, & HPE — 2026-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_8SMqUh4VL-U

### [Plug-in hybrid: deterministic solving engine to combine with LLMs](https://bremen.aitinkerers.org/talks/rsvp_Dk-hX27J8AE)

Python ply Parsers convert quantitative models into graphs, which are used as a basis for dynamic decision solving.

- Event context: AI Tinkerers Bremen — 2026-03-25 — Bremen
- Public talk page: https://bremen.aitinkerers.org/talks/rsvp_Dk-hX27J8AE

### [Grok like system but home made](https://montreal.aitinkerers.org/talks/rsvp_4jmt53Nli5M)

Scrappy implementation of how you can use tool base model to fetch from database / web url or even other to enable end user into a SQL like language for your own workflow in simple

- Event context: AI Tinkerers Montreal - February 2026 Meetup — 2026-02-24 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_4jmt53Nli5M

### [Oracle & NVIDIA AI‑Q: A Blueprint for High‑Performance Research Automation](https://singapore.aitinkerers.org/talks/rsvp_M4Vy0ySvk_Y)

Oracle & Nvidia will be presenting a technical deep-dive demo of an AI Research Assistant built using the NVIDIA AI‑Q blueprint approach, implemented with an enterprise-grade Oracle + NVIDIA stack—using Oracle Database 26ai as the system of record for vectors and retrieval, and NVIDIA’s accelerated AI software for embedding, retrieval optimization, and inference. At a high level, this presentation shows how to build and run a production-ready Retrieval-Augmented Generation (RAG) + agentic workflow where: Enterprise documents are ingested and embedded, using NVIDIA’s AI software stack (including NIM microservices and retrieval components). Embeddings are stored directly inside Oracle Database 26ai using its native VECTOR data type—so we don’t need a separate vector database. Semantic retrieval happens in Oracle Database 26ai using SQL (AI Vector Search), enabling vector similarity search combined with enterprise relational filters and governance. The retrieved context is then fed into a reasoning model to generate grounded answers and structured insights. What the Audience Will Learn / Take Away 1) How Oracle + NVIDIA changes enterprise AI architecture NVIDIA AI Enterprise is available natively through the OCI Console, reducing friction in provisioning AI software and accelerating adoption. Oracle and NVIDIA are co‑engineering deeper integrations, including NVIDIA NIM microservices support and NeMo Retriever integration with Oracle Database 26ai, enabling smoother RAG pipelines. 2) Why Oracle Database 26ai is a key differentiator for RAG Instead of deploying a separate vector DB, I’ll show how Oracle Database 26ai provides AI Vector Search directly inside the database, using the VECTOR data type—letting teams store embeddings next to business data and query semantically in SQL. 3) How to build a faster, simpler, more governable RAG workflow The demo will highlight architectural improvements that enterprise teams care about: - fewer moving parts, - less data duplication, - simpler security and governance patterns, - and a clean operational model that aligns with existing Oracle enterprise data platforms. What we’ll Show in the Demo (Step-by-Step) - Document ingestion (technical PDFs and enterprise materials) - Embedding generation using NVIDIA-optimized AI tooling (NIM microservices / retrieval stack). - Semantic retrieval using Oracle AI Vector Search in SQL (top‑K similarity search + filters). - Answer generation using reasoning over retrieved context

- Event context: AI Tinkerers - The Age of AI & Infrastructure (Singapore) — 2026-02-11 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_M4Vy0ySvk_Y

### [Neo4j + Python para análise de redes de colaboração científica](https://saopaulo.aitinkerers.org/talks/rsvp_vsdk71Al65k)

Nesta demo, Pedro Sader Azevedo apresentará como utilizou o Neo4j para transformar dados de coautoria científica em um grafo de colaboração acadêmica, revelando as comunidades ocultas que moldam as redes de pesquisa. Serão abordados os fundamentos da modelagem de dados em grafos, bem como as melhores ferramentas para ciência de dados neste contexto. Além disso, você descobrirá padrões inesperados na vida acadêmica, que revelam o que (ou quem) pode impulsionam seu reconhecimento no mundo da ciência.

- Event context: Ai Tinkerers São Paulo na ESPM com Neo4j e Oracle - Novembro 2025 — 2025-11-27 — São Paulo
- Public talk page: https://saopaulo.aitinkerers.org/talks/rsvp_vsdk71Al65k

### [Sales Assistant Agent on Snowflake, integrating Claude 3.5 Sonnet](https://nyc.aitinkerers.org/talks/rsvp_cnnfABUQSZg)

This project develops a Sales Assistant Agent using data tools in Snowflake Cortex. The Agent is able to analyze structured and unstructured data (PDFs and images), classify data, and make data searchable through Cortex Search.

- Event context: November Demo Day ft. Google Cloud and CopilotKit — 2025-11-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_cnnfABUQSZg

### [SQL-First AI Memory: Building Developer Tools with WebMCP and Browser-Native Databases](https://seattle.aitinkerers.org/talks/rsvp_sbvhzQ05BHQ)

Embeddings and semantic search were the first tools of choice to augment AIs with memory and help reduce hallucinations. Nowadays, however, most SOTA memory systems do not use embeddings or semantic search at all and instead let the AI explore a knowledge base with SQL. I'll demonstrate a live developer workflow where an AI agent uses WebMCP tools to query a PostgreSQL database running entirely in the browser (PG-Lite + WASM). You'll see the AI's SQL reasoning process in real-time as it explores project context, relationships between entities, and builds up understanding through structured queries rather than vector similarity.

- Event context: AI Tinkerers Seattle Meetup: Dev Tools Track — October 6, 2025 — 2025-10-07 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_sbvhzQ05BHQ

### [Data Pipelines for Everyone](https://london.aitinkerers.org/talks/rsvp_yxX00gkMXAg)

We're presenting a PoC to allow any non-technical business user to explore their data, build data processing pipelines for it, and allow them to make updates with high confidence, without having to understand or touch any code.

- Event context: AI Tinkerers London Meetup - July 16th, 2025 — 2025-07-16 — London
- Public talk page: https://london.aitinkerers.org/talks/rsvp_yxX00gkMXAg

### [Translating Financial Data into Qualitative Insights](https://nyc.aitinkerers.org/talks/rsvp_jZXxpn6QCHo)

I will show how you can take ANY csv of financial data and use Ai to create long term structured memory using a knowledge graph that will be used to automate financial analysis. I will show the prompt structure/system and how it is used to create nodes and edges that are highly dense in context and can be retrieve to store tasks.

- Event context: AI Tinkerers NYC Meetup - March 2025 Sponsored by SignalFire and Comet — 2025-03-04 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_jZXxpn6QCHo

### [Completely local RAG in low code with Deepseek-r1:7b and Flowise](https://abu-dhabi.aitinkerers.org/talks/rsvp_-yXkOv-2nKk)

With the recent evolution in small performant models, it is quite possible now to replace openai api with a locally running deepseek-r1:7b model. In this demo will showcase how you can quickly run a completely locally Hosted RAG flow retreiving data from an sql based database when prompting for data such as list the companies with highest sales last year in technology sector, the flow will extraxt the ddl, understand the schema, generate the required sql query statement and then return the results and run them through deepseek again to generate a user friendly answer in a chat experience.

- Event context: AI Tinkerers - Abu Dhabi Meetup #3 (Feb 2025) — 2025-02-21 — Abu Dhabi
- Public talk page: https://abu-dhabi.aitinkerers.org/talks/rsvp_-yXkOv-2nKk

### [Chat with your Strava data: Multi-agentic workflow that translates NL to SQL and generate visualizations and responses](https://singapore.aitinkerers.org/talks/rsvp_nbGxlzdp_jA)

Multi-agentic workflow that translates NL into SQL, executes with built-in debugging capabilities and generate contextually appropriate visualizations and responses. Users can explore their Strava workout data by simply asking questions after granting access via Strava OAuth.

- Event context: AI Tinkerers Singapore: 5th Meetup - February 21st, 2025 — 2025-02-21 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp_nbGxlzdp_jA

### [Missing Persons in Detroit NL2SQL Bot](https://seattle.aitinkerers.org/talks/rsvp__IaqdyP8HQ0)

An ingestion and enhancement engine for PDFs containing information about people reported missing in Detroit. Journalists can ask natural language questions of the structured data directly where they work, in Microsoft Teams, aiding their reporting.

- Event context: AI Tinkerers Seattle - Women in AI Gathering — 2024-12-06 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp__IaqdyP8HQ0

### [From Haikus to Helper - Wrangling Agentic LLM's](https://montreal.aitinkerers.org/talks/rsvp_ykR1yUDQJ08)

We built a product that uses LLM's for data transformations + enrichment ( think spreadsheet) but also supports Agentic responses/actions on these datasets. I'll do a brief demo of the product and describe the architecture and challenges productizing augmentation and agentic behaviours. We'll walk through adding an AI enrichment column, and specifically cover: * The path of data through the system: Ingestion => SQL / Vectorization => Retrieval, * LLM touch points - importance estimation, schema prediction, extraction/augmentation. Use the agent to analyze results and support the user: * Prepare a report, have it posted to slack

- Event context: AI Tinkerers - Montreal Inaugural Meetup (October) — 2024-10-29 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_ykR1yUDQJ08

### [Empowering AI Agents with Human Oversight: A Toolkit for Safe Tool Access](https://nyc.aitinkerers.org/talks/rsvp_spyMFcD8x8o)

I've been hacking on a python toolkit to enable AI agents to communicate with humans in tool-based and asynchronous workflows. I'll show how HumanLayer can be used to gate access to high-stakes function calls like "email_customer" or "run_production_sql_query", requiring human approval in slack before executing the tool. Time permitting, I'll also go into a (very WIP) version of a more generic "human as tool" that enables an agent to consult various members of a team for advice and questions. I can talk about challenges with different tool-calling models and how I improved agent accuracy in calling the correct tool.

- Event context: End of Summer Technical Founder BBQ — 2024-09-17 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_spyMFcD8x8o

### [Using HumanLayer to give agents safe access to high-stakes tools](https://sf.aitinkerers.org/talks/rsvp_CnCcIGUYDbw)

I've been hacking on a python toolkit to enable AI agents to communicate with humans in tool-based and asynchronous workflows. I'll show how HumanLayer can be used to gate access to high-stakes function calls like "email_customer" or "run_production_sql_query", requiring human approval in slack before executing the tool. Time permitting, I'll also go into a (very WIP) version of a more generic "human as tool" that enables an agent to consult various members of a team for advice and questions. I can talk about challenges with different tool-calling models and how we improved agent accuracy in calling the correct tool.

- Event context: AI Tinkerers - San Francisco - August 2024 Meetup — 2024-08-22 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_CnCcIGUYDbw

### [Unlocking Insights from Tabular Data with LLMs](https://toronto.aitinkerers.org/talks/rsvp_EVqtcfX0ujE)

This application demonstrates how we can leverage Large Language Models (LLMs) to extract valuable insights directly from your company's tabular data. Unlike unstructured data (PDFs, Docs etc.) that require Retrieval-Augmented Generation (RAG) techniques, this approach allows LLMs to interact with structured data in a more efficient way. Here's how it works: Natural Language Understanding with LLM: The user submits a question in plain text. The LLM parses this question to understand its intent and the relevant data points needed. SQL Query Generation: Based on the understanding, the LLM generates a corresponding SQL query to retrieve the desired information from your company's data warehouse. Data Retrieval and Summarization: The generated SQL query is executed, fetching the relevant data points. Finally, the LLM summarizes the retrieved data in a clear and concise manner, providing a comprehensive answer to the user's initial question.

- Event context: AI Tinkerers - Toronto - June 2024 Meetup — 2024-06-27 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_EVqtcfX0ujE

### [Einblick Prompt AI](https://nyc.aitinkerers.org/talks/rsvp_egOXGJglcEc)

Tell your data notebook what to do. Meet Einblick, the AI-native notebook that writes and fixes code, plots beautiful charts, builds models, and much more. Provide a prompt and Einblick’s AI agent builds workflows using Python, SQL, and interactive components.

- Event context: AI Tinkerers NYC Inaugural Meetup - August — 2023-08-01 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_egOXGJglcEc

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Slack](https://aitinkerers.org/technologies/slack) ([Markdown](https://aitinkerers.org/technologies/slack.md)) — 15 public demos
- [BERT](https://aitinkerers.org/technologies/bert) ([Markdown](https://aitinkerers.org/technologies/bert.md)) — 179 public demos
- [BLOOM](https://aitinkerers.org/technologies/bloom) ([Markdown](https://aitinkerers.org/technologies/bloom.md)) — 115 public demos
- [GPT-3](https://aitinkerers.org/technologies/gpt-3) ([Markdown](https://aitinkerers.org/technologies/gpt-3.md)) — 191 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [HumanLayer](https://aitinkerers.org/technologies/humanlayer) ([Markdown](https://aitinkerers.org/technologies/humanlayer.md)) — 3 public demos
- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [Llama-2](https://aitinkerers.org/technologies/llama-2) ([Markdown](https://aitinkerers.org/technologies/llama-2.md)) — 227 public demos
- [LLM](https://aitinkerers.org/technologies/llm) ([Markdown](https://aitinkerers.org/technologies/llm.md)) — 123 public demos
- [Neo4j](https://aitinkerers.org/technologies/neo4j) ([Markdown](https://aitinkerers.org/technologies/neo4j.md)) — 29 public demos
- [PaLM 2](https://aitinkerers.org/technologies/palm-2) ([Markdown](https://aitinkerers.org/technologies/palm-2.md)) — 116 public demos
- [RAG](https://aitinkerers.org/technologies/rag) ([Markdown](https://aitinkerers.org/technologies/rag.md)) — 147 public demos
- [RoBERTa](https://aitinkerers.org/technologies/roberta) ([Markdown](https://aitinkerers.org/technologies/roberta.md)) — 118 public demos
- [Chrome Extensions](https://aitinkerers.org/technologies/chrome-extensions) ([Markdown](https://aitinkerers.org/technologies/chrome-extensions.md)) — 3 public demos
- [Chrome MV3](https://aitinkerers.org/technologies/chrome-mv3) ([Markdown](https://aitinkerers.org/technologies/chrome-mv3.md)) — 2 public demos
- [Cloudflare](https://aitinkerers.org/technologies/cloudflare) ([Markdown](https://aitinkerers.org/technologies/cloudflare.md)) — 17 public demos
- [CrewAI](https://aitinkerers.org/technologies/crewai) ([Markdown](https://aitinkerers.org/technologies/crewai.md)) — 15 public demos