Guglielmo Paesano AI engineer and founder of AIGROW

I build AI systems that do people's work, and I measure where they still need people.

contact@guglielmo.ioDiscord, 4K members

Research: what I measure, published with its data

I study what AI models do when they are given real work, and I publish the data and the method so anyone can check the result. One paper, one monthly dataset, one benchmark and one study so far.

  • Paper

    Instrument before you evaluate

    Write-path invariants for deployed human-agent systems

    A field report from a production human-agent system. Whether such a system can be evaluated is decided by its write path: what it records, with what attribution, and what it may overwrite. The paper names four write-path invariants and closes with a checklist a team can answer before it designs an evaluation.

    Authors
    Guglielmo Paesano, Romanus Berg
    Venue
    Human-AI Coevolution (HAIC) workshop, NeurIPS 2026
    Accepted
    30 Sep 2026
    Presentation
    Atlanta, 13 December 2026

    OpenReview(verifiable source, opens in a new tab)What the paper argues

  • 80,059DOI10.5281/zenodo.23188442
    Open dataset, monthly

    AI Visibility Index

    October 2026 edition

    Which businesses do AI assistants recommend when people ask them? Each month the same questions go to four assistants in every place and language on the list, and every answer is kept and published through AIGROW, the company I founded.

    Answers recorded
    80,059
    Assistants asked
    ChatGPT, Claude, Gemini, Grok
    Countries
    20
    Languages
    11
    Places
    108
    Business types
    44
    Licence
    CC BY 4.0

    DOI 10.5281/zenodo.23188442(verifiable source, opens in a new tab)aigrow.gg/index(verifiable source, opens in a new tab)

  • 71.5%
    Benchmark, pilot edition

    Which office work a model can be left alone with

    36 models on 20 office tasks, 720 graded runs. 515 passed, 71.5% overall. The mean hides the finding: the same models that route a request almost perfectly fail most of the time at replying to a review.

Pass rate by kind of work, AIGROW office task benchmark, pilot edition, 23 Sep 2026
Kind of workPassedRate
Request routing69 of 7295.8%
Invoice extraction65 of 7290.3%
Email triage30 of 3683.3%
Meeting summary30 of 3683.3%
Business calculation55 of 7276.4%
Lead qualification26 of 3672.2%
Bookkeeping51 of 7270.8%
Appointment scheduling50 of 7269.4%
Policy questions25 of 3669.4%
Customer support48 of 7266.7%
Product description21 of 3658.3%
Quote writing37 of 7251.4%
Review replies8 of 3622.2%

Every task and its grading(verifiable source, opens in a new tab)CC BY 4.0

Also published

The same method, on your system

A system I build for a client is instrumented the way these studies are: it records what it did, attributed and append-only, so whether it works is answered from data. If you already run an AI system and cannot say how well it performs, that is a project of its own.

LLM evaluation, as a serviceCan AI do it? Work tasks, tested in public

Have a system that needs measuring?

Tell me what it does and what you need to know about it. I read every brief myself and answer in writing with a scope.

Or write to contact@guglielmo.io

The human check appears here.

No calls and no sales sequence. One written answer from me.