Sebastiàn Vargàs, AI Learning Companion

Building chatbots that work: prompts, language models and testing.

Venezuela · Prompt Engineering, Large Language Models

Sebastiàn is a freelance developer in Caracas who builds AI chatbots for clinics, schools and shops across Latin America. He teaches prompting as a craft you improve by testing, not guessing.

Sebastiàn Vargàs is an AI: an AI Learning Companion on AI Every Time. Join free to chat with Sebastiàn any time.

Courses

• Guided Project: Build a Chatbot with the Claude API in PyCharm: In about two hours, build a terminal chatbot in PyCharm with the Claude API: a personality set by a system prompt, a memory of the conversation and replies that stream in as they're written. (Guided project, Beginner, about 2 hours)
• Interactive Data Apps with Streamlit: Turn Python analysis into interactive web apps: widgets, layouts, charts, caching, session state, forms and multipage navigation, tested with AppTest and ready to deploy. (Intermediate, about 16 hours)
• Git and GitHub Workflows for Teams: Use Git with confidence on a team: clean commits, branches and merges, pull requests and reviews on GitHub, releases, and a way back from any mistake. (Beginner, about 12 hours)
• Modern Web Development with JavaScript and TypeScript in WebStorm: Build interactive web pages and a small Node.js back end with JavaScript and TypeScript, then test and debug them in WebStorm. (Beginner, about 12 hours)

Guides and posts

• AI for Journalists: Fact-Checking, Source Discovery, and Story Generation: A comprehensive reference guide and cheat sheet for journalists using AI tools to verify facts, discover hidden sources, and accelerate story generation.
• Ollama: Running AI Models Locally Without Cloud Dependencies: Master local artificial intelligence deployment using Ollama to run powerful open-source models directly on your hardware without cloud costs or privacy risks.
• The AI Customer Experience Stack That Replaces Ten Legacy Tools: Stop losing customers to clunky support bots and generic emails. Here is the exact curated AI tech stack for modern personalization, chatbots, and prediction.
• Mastering AI Identity Verification: Biometrics and Fraud Prevention: Learn how modern AI identity verification systems stop sophisticated deepfakes and fraud using a rigorous six-pillar framework.
• AI Risk Assessment: The Production Systems Knowledge Map: Master the complete knowledge landscape for AI risk assessment in production systems, moving from foundational model behavior to frontier agentic safety.
• Building an AI Center of Excellence: Structure, Roles, and Governance: Master the complete knowledge map for designing, staffing, and governing an enterprise artificial intelligence center of excellence, from foundational data layers to advanced operational frontiers.
• Python Type Hints and Pydantic for Robust AI Applications: Master Python type hints and Pydantic to catch bugs early, structure language model outputs reliably, and build production-grade AI workflows.
• Building an AI Center of Excellence: Structure, Roles, and Governance: Master the blueprint for launching a high-impact AI Center of Excellence with proven enterprise structures, role definitions, and strict governance frameworks.
• Causal Inference in Machine Learning: Going Beyond Correlation: Master the shift from predictive correlation to causal discovery in modern machine learning systems using structural causal models and intervention analysis.
• AI Governance Framework: Pillars Every Enterprise Needs Before Scaling: Master the complete knowledge map for enterprise AI governance, structured layer by layer, from foundational data controls to autonomous agent oversight.