Anastasios Stamoulakatos

Anastasios Stamoulakatos

Data Scientist at Satalia | PhD in Applied AI

Unlocking the Power of Multimodal Embeddings: A Hands-on Guide

less than 1 minute read

Published:

Multimodal embeddings allow us to represent diverse data types—such as text, images, audio, and geospatial coordinates—within a shared vector space, enabling advanced semantic search and cross-modal reasoning.

In this hands-on guide published on Medium, I cover the key concepts of multimodal AI and walk through a modular reference implementation for embedding similarity.

Read the full article on Medium

Check out the accompanying code repository here: GitHub Repository

Agentic Data Guardian: Enterprise Data Quality Management

less than 1 minute read

Published:

Designed and built AI multi-agent workflows to automate the detection and remediation of data quality anomalies in enterprise databases. Implemented Google ADK and AutoGen agents that continuously validate and update schemas, keeping model answers grounded and reducing hallucinations.

Creative AI: Evaluating and Ranking AI Creativity

less than 1 minute read

Published:

Researched multi-agent collaboration strategies and LLM-as-a-judge paradigms to evaluate and rank creative outputs. Benchmarked agent architectures (CrewAI, AutoGen, LangGraph) on creative marketing tasks.

Strava Activity to Google Sheets Sync

less than 1 minute read

Published:

Automation project to sync Strava training/activity logs directly into Google Sheets using the Strava API and Google Sheets API. Implemented automated OAuth token rotation and scheduled cron-like syncing.

Retrieval-Augmented Generation (RAG) 101

less than 1 minute read

Published:

Retrieval-Augmented Generation (RAG) bridges the gap between static LLM parameters and dynamic external data. In this guide, I break down the core components of a RAG pipeline—from document chunking and vector embeddings to context retrieval and generation—and explain how real-time tools like Web Search integration keep model answers accurate and grounded.