Skip to content
Federico MeiniReal-time systems, AI agents & more
  • Services
  • Work
  • Blog
  • About
IT
  • Services
  • Work
  • Blog
  • About
  • Contact
Work with me→(opens in a new tab)
← All posts

#python

  • 16 Sept 2026

    Testing a medical triage agent with LangWatch Scenario and pytest

    How I test a medical triage AI agent with LangWatch Scenario: a simulated user, judge criteria, scripted and free-running conversations, in pytest and CI.

    8 min read#ai-agents#llm-evals#python

    →
  • 30 Jun 2026

    Simulation evals: letting an LLM play the user to test your chatbot before real users do

    How to build simulation evals for LLM chatbots: persona-driven simulated users, LLM-as-judge rubrics, error rates for high-stakes flows and a feedback loop.

    8 min read#ai-agents#llm-evals#llm-as-judge

    →

Available for freelance work

Have a system that needs to scale, or an agent that needs to be trusted?

Start a conversation →(opens in a new tab)How engagements work

Services

  • WhatsApp Business Platform
  • Real-time systems
  • PostgreSQL & Elasticsearch
  • AI agents & evals
  • Agentic coding

Site

  • Selected work
  • Blog
  • About
  • Contact

Elsewhere

  • GitHub
  • LinkedIn
  • Email
  • RSS

For machines

  • llms.txt
  • llms-full.txt
  • Sitemap
© 2026 Federico Meini · VAT IT01966540492No cookies. Static HTML, cookieless analytics.