Data and AI group, learning, and practice

FREE data + AI knowledge sessions to help each others and learn from each other

Session 2: Cloud Infrastructure — AWS, GCP, Snowflake & Vibe-Coding Your Infra
Practical infrastructure for personal projects and small teams. Compute, storage, databases, cost control — and how AI writes your Terraform and Docker configs now.
Demo (~15 min): SSH into EC2 — systemd, Docker Postgres, Nginx, SSL. GCP console: BigQuery, billing. Snowflake: sample warehouse, time travel. Run Ollama locally — compare vs cloud API.
AI Hands-on (~15 min): Live vibe-coding: use Claude Code to generate a Dockerfile + docker-compose.yaml for a Postgres + FastAPI setup. Show the AI reading requirements, writing config, fixing errors. Audience follows along or suggests changes.
Open Floor (~20 min): What cloud do you use and why? Any job opportunny to share

***

| Session | Special Topic | AI Component |
| ------- | ------------- | ------------ |
| 1 | Data & AI Ecosystem overview | First prompt challenge — everyone builds something |
| 2 | Cloud Infrastructure (AWS/GCP/Snowflake) | Vibe-code a Dockerfile + docker-compose with AI |
| 3 | Data Pipelines & Quality | AI anomaly detection on messy data |
| 4 | Analytics & BI | Text-to-SQL — ask your database in English |
| 5 | ML Evaluation & Backtesting | AI as model critic — "what's wrong with my eval?" |
| 6 | LLMs Deep Dive | Live model shootout — 4 models, same prompt, group scores |
| 7 | AI Agents — Tools, RAG, Memory | Vibe-code a working agent together |
| 8 | Multi-Agent Systems | Group design exercise — sketch a multi-agent for your problem |
| 9 | Vibe Coding Deep Dive | Build a complete feature live with AI |
| 10 | Show-and-Tell & Opportunities | Community demos + jobs + what's next |

FREE data + AI knowledge sessions to help each others and learn from each other, share job opportunity

Session 3: Data Pipelines & Quality — AI-Powered Validation and Anomaly Detection
Pipelines, ingestion, and the step everyone skips: validation. Plus how LLMs can now detect data anomalies that rule-based checks miss.
Demo (~15 min): Airflow DAG chain. Run a validation script comparing computed metrics against a reference source — all matching at 0.0 difference. Show the 40-point bug story and the fix.
AI Hands-on (~15 min): Feed a messy sample dataset to an LLM: "Here are 50 rows of data. Find anomalies, missing values, and anything suspicious." Compare what Gemini vs Claude catches. Discuss: would you trust AI for data quality in your pipeline?
Open Floor (~20 min): Worst data quality horror story? What validation patterns work at scale? Anyone using AI for data profiling or documentation? What do you wish upstream teams did differently? Any job opportunny to share

***

| Session | Special Topic | AI Component |
| ------- | ------------- | ------------ |
| 1 | Data & AI Ecosystem overview | First prompt challenge — everyone builds something |
| 2 | Cloud Infrastructure (AWS/GCP/Snowflake) | Vibe-code a Dockerfile + docker-compose with AI |
| 3 | Data Pipelines & Quality | AI anomaly detection on messy data |
| 4 | Analytics & BI | Text-to-SQL — ask your database in English |
| 5 | ML Evaluation & Backtesting | AI as model critic — "what's wrong with my eval?" |
| 6 | LLMs Deep Dive | Live model shootout — 4 models, same prompt, group scores |
| 7 | AI Agents — Tools, RAG, Memory | Vibe-code a working agent together |
| 8 | Multi-Agent Systems | Group design exercise — sketch a multi-agent for your problem |
| 9 | Vibe Coding Deep Dive | Build a complete feature live with AI |
| 10 | Show-and-Tell & Opportunities | Community demos + jobs + what's next |

FREE data + AI knowledge sessions to help each others and learn from each other, share job opportunity

Session 4: Analytics & Natural Language BI — Ask Your Database a Question
AI turns databases into conversational interfaces. This session covers text-to-SQL, AI-generated insights, and how analysts are using LLMs daily.
Demo (~15 min): Open a data explorer with thousands of records and filters. Ask an AI copilot a natural language question — show it querying the database. BigQuery Studio: Gemini generating SQL from English.
AI Hands-on (~15 min): Everyone tries text-to-SQL. Give the group a sample schema and 5 business questions. Use free Gemini/ChatGPT to generate SQL. Compare: which model writes better queries? Which ones hallucinate table names? How do you ground the AI in your actual schema?
Open Floor (~20 min): BAs and DAs: how has AI changed your daily work? Anyone built a natural language BI tool? PMs: using AI for product decisions? What's the gap between AI analytics promise vs reality?

***

| Session | Special Topic | AI Component |
| ------- | ------------- | ------------ |
| 1 | Data & AI Ecosystem overview | First prompt challenge — everyone builds something |
| 2 | Cloud Infrastructure (AWS/GCP/Snowflake) | Vibe-code a Dockerfile + docker-compose with AI |
| 3 | Data Pipelines & Quality | AI anomaly detection on messy data |
| 4 | Analytics & BI | Text-to-SQL — ask your database in English |
| 5 | ML Evaluation & Backtesting | AI as model critic — "what's wrong with my eval?" |
| 6 | LLMs Deep Dive | Live model shootout — 4 models, same prompt, group scores |
| 7 | AI Agents — Tools, RAG, Memory | Vibe-code a working agent together |
| 8 | Multi-Agent Systems | Group design exercise — sketch a multi-agent for your problem |
| 9 | Vibe Coding Deep Dive | Build a complete feature live with AI |
| 10 | Show-and-Tell & Opportunities | Community demos + jobs + what's next |

FREE data + AI knowledge sessions to help each others and learn from each other

Session 5: ML Evaluation & Backtesting — How to Know If Your AI Actually Works
Everyone builds models. Few test honestly. This session covers evaluation methodology plus using AI agents to automate the testing process.
Demo (~15 min): Run a backtest on sample data. Show honest results: some approaches work (59%), some don't (49% — worse than random). Run an optimizer across 1,000 parameter combinations.
AI Hands-on (~15 min): Give an LLM your model's evaluation results and ask it to critique: "Here are my model metrics. What's wrong with my evaluation? What am I missing? How could I be fooling myself?" Compare how different models challenge your assumptions. Surprisingly useful for catching blind spots.
Open Floor (~20 min): How do you evaluate models in practice? A model that looked great in testing but failed in production — what happened? How do you explain model performance to non-technical stakeholders? Share your evaluation frameworks.

***

| Session | Special Topic | AI Component |
| ------- | ------------- | ------------ |
| 1 | Data & AI Ecosystem overview | First prompt challenge — everyone builds something |
| 2 | Cloud Infrastructure (AWS/GCP/Snowflake) | Vibe-code a Dockerfile + docker-compose with AI |
| 3 | Data Pipelines & Quality | AI anomaly detection on messy data |
| 4 | Analytics & BI | Text-to-SQL — ask your database in English |
| 5 | ML Evaluation & Backtesting | AI as model critic — "what's wrong with my eval?" |
| 6 | LLMs Deep Dive | Live model shootout — 4 models, same prompt, group scores |
| 7 | AI Agents — Tools, RAG, Memory | Vibe-code a working agent together |
| 8 | Multi-Agent Systems | Group design exercise — sketch a multi-agent for your problem |
| 9 | Vibe Coding Deep Dive | Build a complete feature live with AI |
| 10 | Show-and-Tell & Opportunities | Community demos + jobs + what's next |