DSPT x Devscope: All about AI Agents

DSPT presents
From Development to Evaluations - All about AI Agents

AI Agents are transforming the way we build software, automate workflows, and design intelligent systems. In this meetup, we’ll dive into both sides of agent development: building powerful GenAI-driven workflows and ensuring they are trustworthy, measurable, and robust.

Coding in the Age of Agents, by Rui Quintino
Using the latest coding agents like Claude Code and GitHub Copilot, we’ll explore how GenAI and agentic loops are changing the way we build software. Are these just “stochastic parrots”… or something more? And in this new stack, what role is left for us?

Your Agent needs some Evals, by Pedro Azevedo
Developing robust GenAI agents is best done with Eval Driven Development (EDD). In this session you'll learn how you can implement EDD by making evaluation a first-class citizen throughout your development cycle. We will cover the practical steps of defining relevant metrics and building comprehensive test sets for GenAI's and LLMOps unique challenges. Crucially, we'll demonstrate how to leverage open-source tools like MLflow to streamline this process, enabling you to track, compare, and version evaluation results alongside your models for truly reproducible and data-driven AI development.

Agenda
18h00: Get together
18h15: Talk: "Your Agent needs some Evals", with Pedro Azevedo
18h45: Coffee Break + Networking
19h15: Talk: "Coding in the Age of Agents", with Rui Quintino
20h00: Closing remarks

Can make it in person? We'll share a link for participants who want to join online 🤝
Reserve your spot today and don’t forget to add the event to your calendar!