Skip to content
View emmepra's full-sized avatar

Highlights

  • Pro

Block or report emmepra

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
emmepra/README.md

Matteo Prandi

CTO at Icaro Lab, working across AI safety, model evaluation, and research engineering.

I build infrastructure for studying how AI models and agents behave in practice: their capabilities, failure modes, interactions, and effects on work and organizations.

Selected work

  • MASE: infrastructure for controlled multi-agent experiments.
  • Adversarial Humanities Benchmark: evaluating refusal robustness under adversarial reformulations.
  • Ora et Labora: repo-first workflows for coding and research agents.
  • Ars Operandi: operational adapters and safety boundaries for agentic workflows.

Website · LinkedIn · ORCID

Pinned Loading

  1. icaro-lab/MASE icaro-lab/MASE Public

    Experimentation infrastructure for authoring, running, and inspecting controlled multi-agent AI simulations.

    Python 5 2

  2. icaro-lab/ahb icaro-lab/ahb Public

    AI safety benchmark for testing refusal robustness under humanities-inspired adversarial reformulations.

    Python 3

  3. ora-et-labora ora-et-labora Public

    Reusable Codex workflow skills with repo-first issue-to-release discipline

    Python 1 1

  4. ars-operandi ars-operandi Public

    Provider-specific operational adapter skills for Codex, complementing Ora et Labora.

    Python 1