A-01 Letter
Matias Lapolla
Hi, I’m Matias Lapolla. I build AI-native products at Persiscal, mostly agent platforms. On the side I run Senda, where I ship software experiments with AI agents. Each one starts by defining its acceptance criteria, because I believe an agent is only as good as the evals you run on it. I write about building with agents: why the tool description matters more than the code and what memory is for. My CV has the rest, the blog has every article, and you can reach me on X.
A-02
Writing
- So You Want to Build AI Agents That Do the Work? Start with Evals 34 min
- Mastra Memory: The Context Layer That Survives Long Conversations 20 min
- MCP: Why the Description String Is the Most Important String in Your Harness 23 min
- Mastra Processors: la capa de guardrails que se ejecuta en cada paso 12 min
- Mastra Processors: The Guardrail Layer That Runs on Every Step 10 min
- Building a Fully Functional Agent Harness with Mastra 12 min
- Foundations of AI: From Vectors to Neural Networks 22 min
- Vibe Engineering: A Guide to AI-Assisted Coding with Agents 12 min
- How I Use AI and LLMs for Coding - A Comprehensive and Opinionated Guide 20 min
- Model Context Protocol (MCP) - The USB-C for AI 6 min
A-03
Work
A-04